Explanatory interactive learning (XIL) enables users to guide model training in machine learning (ML) by providing feedback on the model's explanations, thereby helping it to focus on features that are relevant to the prediction from the user's perspective. In this study, we explore the capability of this learning paradigm to mitigate bias and spurious correlations in visual classifiers, specifically in scenarios prone to data bias, such as gender classification. We investigate two methodologically different state-of-the-art XIL strategies, i.e., CAIPI and Right for the Right Reasons (RRR), as well as a novel hybrid approach that combines both strategies. The results are evaluated quantitatively by comparing segmentation masks with explanations generated using Gradient-weighted Class Activation Mapping (GradCAM) and Bounded Logit Attention (BLA). Experimental results demonstrate the effectiveness of these methods in (i) guiding ML models to focus on relevant image features, particularly when CAIPI is used, and (ii) reducing model bias (i.e., balancing the misclassification rates between male and female predictions). Our analysis further supports the potential of XIL methods to improve fairness in gender classifiers. Overall, the increased transparency and fairness obtained by XIL leads to slight performance decreases with an exception being CAIPI, which shows potential to even improve classification accuracy.

We study how people trade off accuracy when using AI-powered tools in professional versus personal contexts for adoption purposes, the determinants of those trade-offs, and how users cope when AI/apps are unavailable. Because modern AI systems (especially generative models) can produce acceptable but non-identical outputs, we define "accuracy" as context-specific reliability: the degree to which an output aligns with the user's intent within a tolerance threshold that depends on stakes and the cost of correction. In an online survey (N=300), among respondents with both accuracy items (N=170), the share requiring high accuracy (top-box) is 24.1% at work vs. 8.8% in personal life (+15.3 pp; z=6.29, p<0.001). The gap remains large under a broader top-two-box definition (67.0% vs. 32.9%) and on the full 1-5 ordinal scale (mean 3.86 vs. 3.08). Heavy app use and experience patterns correlate with stricter work standards (H2). When tools are unavailable (H3), respondents report more disruption in personal routines than at work (34.1% vs. 15.3%, p<0.01). We keep the main text focused on these substantive results and place test taxonomy and power derivations in a technical appendix.

Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing pedagogical interventions. However, collecting authentic data is challenging due to privacy concerns and the high cost of longitudinal studies. While Large Language Models (LLMs) offer a promising path to student simulation, they suffer from competency bias, optimizing for efficient correctness rather than the erratic, iterative struggle characteristic of novice learners. We present BEAGLE, a neuro-symbolic framework that addresses this bias by incorporating Self-Regulated Learning (SRL) theory into a novel architecture. BEAGLE integrates three key technical innovations: (1) a semi-Markov model that governs the timing and transitions of cognitive behaviors and metacognitive behaviors; (2) Bayesian Knowledge Tracing with explicit flaw injection to enforce realistic knowledge gaps and "unknown unknowns"; and (3) a decoupled agent design that separates high-level strategy use from code generation actions to prevent the model from silently correcting its own intentional errors. In evaluations on Python programming tasks, BEAGLE significantly outperforms state-of-the-art baselines in reproducing authentic trajectories. In a human Turing test, users were unable to distinguish synthetic traces from real student data, achieving an accuracy indistinguishable from random guessing (52.8%).

Alignment research focuses on making individual AI systems reliable. Human institutions achieve reliable collective behaviour differently: they mitigate the risk posed by misaligned individuals through organisational structure. Multi-agent AI systems should follow this institutional model using compartmentalisation and adversarial review to achieve reliable outcomes through architectural design rather than assuming individual alignment. We demonstrate this approach through the Perseverance Composition Engine, a multi-agent system for document composition. The Composer drafts text, the Corroborator verifies factual substantiation with full source access, and the Critic evaluates argumentative quality without access to sources: information asymmetry enforced by system architecture. This creates layered verification: the Corroborator detects unsupported claims, whilst the Critic independently assesses coherence and completeness. Observations from 474 composition tasks (discrete cycles of drafting, verification, and evaluation) exhibit patterns consistent with the institutional hypothesis. When assigned impossible tasks requiring fabricated content, this iteration enabled progression from attempted fabrication toward honest refusal with alternative proposals--behaviour neither instructed nor individually incentivised. These findings motivate controlled investigation of whether architectural enforcement produces reliable outcomes from unreliable components. This positions organisational theory as a productive framework for multi-agent AI safety. By implementing verification and evaluation as structural properties enforced through information compartmentalisation, institutional design offers a route to reliable collective behaviour from unreliable individual components.

Prompt design significantly impacts the moral competence and safety alignment of large language models (LLMs), yet empirical comparisons remain fragmented across datasets and models.We introduce ProMoral-Bench, a unified benchmark evaluating 11 prompting paradigms across four LLM families. Using ETHICS, Scruples, WildJailbreak, and our new robustness test, ETHICS-Contrast, we measure performance via our proposed Unified Moral Safety Score (UMSS), a metric balancing accuracy and safety. Our results show that compact, exemplar-guided scaffolds outperform complex multi-stage reasoning, providing higher UMSS scores and greater robustness at a lower token cost. While multi-turn reasoning proves fragile under perturbations, few-shot exemplars consistently enhance moral stability and jailbreak resistance. ProMoral-Bench establishes a standardized framework for principled, cost-effective prompt engineering.

It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions. We introduce TemporalBench, a multi-domain benchmark designed to evaluate temporal reasoning behavior under progressively richer informational settings. TemporalBench adopts a four-tier task taxonomy that examines historical structure interpretation, context-free forecasting, contextual temporal reasoning, and event-conditioned prediction across four real-world domains: retail, healthcare, energy, and physical systems. By controlling access to future targets and contextual information, the benchmark enables a diagnostic analysis of whether models can correctly interpret temporal patterns, align them with external context, and adapt predictions when conditions change. Extensive baseline experiments show that strong numerical forecasting accuracy does not reliably translate into robust contextual or event-aware temporal reasoning; instead, existing agent frameworks exhibit fragmented strengths and systematic failure modes that remain largely hidden under forecasting-only benchmarks. The TemporalBench dataset is publicly available at https://huggingface.co/datasets/Melady/TemporalBench, and we additionally provide a public leaderboard at https://huggingface.co/spaces/Melady/TemporalBench_Leaderboard.

In the critical task of making generative models trustworthy and robust, methods for Uncertainty Quantification (UQ) have begun to show encouraging potential. However, many of these methods rely on rigid heuristics that fail to generalize across tasks and modalities. Here, we propose a novel framework for UQ that is highly flexible and approaches or surpasses the performance of prior heuristic methods. We introduce Directional Concentration Uncertainty (DCU), a novel statistical procedure for quantifying the concentration of embeddings based on the von Mises-Fisher (vMF) distribution. Our method captures uncertainty by measuring the geometric dispersion of multiple generated outputs from a language model using continuous embeddings of the generated outputs without any task specific heuristics. In our experiments, we show that DCU matches or exceeds calibration levels of prior works like semantic entropy (Kuhn et al., 2023) and also generalizes well to more complex tasks in multi-modal domains. We present a framework for the wider potential of DCU and its implications for integration into UQ for multi-modal and agentic frameworks.

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection heuristics are largely text-centric (e.g., perplexity (PPL) filtering) and can prefer fluent yet acoustically mismatched hypotheses, leading to error amplification when fine-tuning. To address this, we introduce a multimodal consistency-guided, reference-free data selection pipeline for ASR accent adaptation under a transductive, label-free protocol. The pipeline starts with a target-aware preselection step based on submodular mutual information to improve query relevance and reduce downstream computation. It then generates multiple pseudo-transcriptions per utterance via perturbation-based decoding and scores each hypothesis using two reference-free signals: speech--text alignment in a shared embedding space and predicted word error rate (WER). A simple percentile-based selection rule retains reliable pseudo-labels for fine-tuning while discarding noisy utterances. In an in-domain setting, selecting ~1.5k utterances from a 30k pool achieves 10.91% WER, close to 10.45% obtained using 30k supervised labels. In a cross-domain setting with a mismatched candidate pool, consistency-filtered subsets avoid the degradation caused by unfiltered pseudo-labels under strong accent shift, and matched-hour experiments on a stronger ASR backbone further confirm gains over random sampling and recent selection baselines.

Frontier language models improve with additional test-time computation, but serial reasoning or uncoordinated parallel sampling can be compute-inefficient under fixed inference budgets. We propose SELFCEST, which equips a base model with the ability to spawn same-weight clones in separate parallel contexts by agentic reinforcement learning. Training is end-to-end under a global task reward with shared-parameter rollouts, yielding a learned controller that allocates both generation and context budget across branches. Across challenging math reasoning benchmarks and long-context multi-hop QA, SELFCEST improves the accuracy-cost Pareto frontier relative to monolithic baselines at matched inference budget, and exhibits out-of-distribution generalization in both domains.

Speech emotion recognition (SER) is essential for humanoid robot tasks such as social robotic interactions and robotic psychological diagnosis, where interpretable and efficient models are critical for safety and performance. Existing deep models trained on large datasets remain largely uninterpretable, often insufficiently modeling underlying emotional acoustic signals and failing to capture and analyze the core physiology of emotional vocal behaviors. Physiological research on human voices shows that the dynamics of vocal amplitude and phase correlate with emotions through the vocal tract filter and the glottal source. However, most existing deep models solely involve amplitude but fail to couple the physiological features of and between amplitude and phase. Here, we propose PhysioSER, a physiology-informed vocal spectrotemporal representation learning method, to address these issues with a compact, plug-and-play design. PhysioSER constructs amplitude and phase views informed by voice anatomy and physiology (VAP) to complement SSL models for SER. This VAP-informed framework incorporates two parallel workflows: a vocal feature representation branch to decompose vocal signals based on VAP, embed them into a quaternion field, and use Hamilton-structured quaternion convolutions for modeling their dynamic interactions; and a latent representation branch based on a frozen SSL backbone. Then, utterance-level features from both workflows are aligned by a Contrastive Projection and Alignment framework, followed by a shallow attention fusion head for SER classification. PhysioSER is shown to be interpretable and efficient for SER through extensive evaluations across 14 datasets, 10 languages, and 6 backbones, and its practical efficacy is validated by real-time deployment on a humanoid robotic platform.

Large language model (LLM) agents have emerged as powerful tools for complex tasks, yet their ability to adapt to individual users remains fundamentally limited. We argue this limitation stems from a critical architectural conflation: current systems treat memory, learning, and personalization as a unified capability rather than three distinct mechanisms requiring different infrastructure, operating on different timescales, and benefiting from independent optimization. We propose MAPLE (Memory-Adaptive Personalized LEarning), a principled decomposition where Memory handles storage and retrieval infrastructure; Learning extracts intelligence from accumulated interactions asynchronously; and Personalization applies learned knowledge in real-time within finite context budgets. Each component operates as a dedicated sub-agent with specialized tooling and well-defined interfaces. Experimental evaluation on the MAPLE-Personas benchmark demonstrates that our decomposition achieves a 14.6% improvement in personalization score compared to a stateless baseline (p < 0.01, Cohen's d = 0.95) and increases trait incorporation rate from 45% to 75% -- enabling agents that genuinely learn and adapt.

Robotic middleware serves as the foundational infrastructure, enabling complex robotic systems to operate in a coordinated and modular manner. In data-intensive robotic applications, especially in industrial scenarios, communication efficiency directly impact system responsiveness, stability, and overall productivity. However, existing robotic middleware exhibit several limitations: (1) they rely heavily on (de)serialization mechanisms, introducing significant overhead for large-sized data; (2) they lack efficient and flexible support for heterogeneous data sizes, particularly in intra-robot communication and Python-based execution environments. To address these challenges, we propose Dataflow-Oriented Robotic Architecture (DORA) that enables explicit data dependency specification and efficient zero-copy data transmission. We implement the proposed framework as an open-source system and evaluate it through extensive experiments in both simulation and real-world robotic environments. Experimental results demonstrate substantial reductions in latency and CPU overhead compared to state-of-the-art middleware.

Natural language explanations play a critical role in establishing trust and acceptance of automated vehicles (AVs), yet existing approaches lack systematic frameworks for analysing how humans linguistically construct driving rationales across diverse scenarios. This paper introduces X-Blocks (eXplanation Blocks), a hierarchical analytical framework that identifies the linguistic building blocks of natural language explanations for AVs at three levels: context, syntax, and lexicon. At the context level, we propose RACE (Reasoning-Aligned Classification of Explanations), a multi-LLM ensemble framework that combines Chain-of-Thought reasoning with self-consistency mechanisms to robustly classify explanations into 32 scenario-aware categories. Applied to human-authored explanations from the Berkeley DeepDrive-X dataset, RACE achieves 91.45 percent accuracy and a Cohens kappa of 0.91 against cases with human annotator agreement, indicating near-human reliability for context classification. At the lexical level, log-odds analysis with informative Dirichlet priors reveals context-specific vocabulary patterns that distinguish driving scenarios. At the syntactic level, dependency parsing and template extraction show that explanations draw from a limited repertoire of reusable grammar families, with systematic variation in predicate types and causal constructions across contexts. The X-Blocks framework is dataset-agnostic and task-independent, offering broad applicability to other automated driving datasets and safety-critical domains. Overall, our findings provide evidence-based linguistic design principles for generating scenario-aware explanations that support transparency, user trust, and cognitive accessibility in automated driving systems.

Code Large Language Models are frequently trained on massive datasets containing restrictively licensed source code. This creates urgent data governance and copyright challenges. Membership Inference Attacks (MIAs) can serve as an auditing mechanism to detect unauthorized data usage in models. While attacks like the Loss Attack provide a baseline, more involved methods like Polarized Augment Calibration (PAC) remain underexplored in the code domain. This paper presents an exploratory study evaluating these methods on 3B--7B parameter code models. We find that while PAC generally outperforms the Loss baseline, its effectiveness relies on augmentation strategies that disregard the rigid syntax of code, leading to performance degradation on larger, complex files. To address this, we introduce AST-PAC, a domain-specific adaptation that utilizes Abstract Syntax Tree (AST) based perturbations to generate syntactically valid calibration samples. Preliminary results indicate that AST-PAC improves as syntactic size grows, where PAC degrades, but under-mutates small files and underperforms on alphanumeric-rich code. Overall, the findings motivate future work on syntax-aware and size-adaptive calibration as a prerequisite for reliable provenance auditing of code language models.

Automated reasoning is critical in domains such as law and governance, where verifying claims against facts in documents requires both accuracy and interpretability. Recent work adopts structured reasoning pipelines that translate natural language into first-order logic and delegate inference to automated solvers. With the rise of large language models, approaches such as GCD and CODE4LOGIC leverage their reasoning and code generation capabilities to improve logic parsing. However, these methods suffer from fragile syntax control due to weak enforcement of global grammar constraints and low semantic faithfulness caused by insufficient clause-level semantic understanding. We propose NL2LOGIC, a first-order logic translation framework that introduces an abstract syntax tree as an intermediate representation. NL2LOGIC combines a recursive large language model based semantic parser with an abstract syntax tree guided generator that deterministically produces solver-ready logic code. Experiments on the FOLIO, LogicNLI, and ProofWriter benchmarks show that NL2LOGIC achieves 99 percent syntactic accuracy and improves semantic correctness by up to 30 percent over state-of-the-art baselines. Furthermore, integrating NL2LOGIC into Logic-LM yields near-perfect executability and improves downstream reasoning accuracy by 31 percent compared to Logic-LM's original few-shot unconstrained translation module.

LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky or negative personas. Most prior work mitigates this issue with training-time solutions (e.g., data curation or alignment-oriented regularization). However, these approaches are costly to maintain as personas and attack strategies evolve, can degrade in-character behavior, and are typically infeasible for frontier closed-weight LLMs. We propose a training-free Dual-Cycle Adversarial Self-Evolution framework with two coupled cycles. A Persona-Targeted Attacker Cycle synthesizes progressively stronger jailbreak prompts, while a Role-Playing Defender Cycle distills observed failures into a hierarchical knowledge base of (i) global safety rules, (ii) persona-grounded constraints, and (iii) safe in-character exemplars. At inference time, the Defender retrieves and composes structured knowledge from this hierarchy to guide generation, producing responses that remain faithful to the target persona while satisfying safety constraints. Extensive experiments across multiple proprietary LLMs show consistent gains over strong baselines on both role fidelity and jailbreak resistance, and robust generalization to unseen personas and attack prompts.

Despite recent advances in artificial intelligence, many systems exhibit stagnation in long-horizon adaptability despite continued performance optimization. This work argues that such limitations do not primarily arise from insufficient learning, data, or model capacity, but from a deeper structural property of how intelligence is optimized over time. We formulate intelligence as a trajectory-level phenomenon governed by multi-objective trade-offs, and introduce Trajectory-Dominant Pareto Optimization, a path-wise generalization of classical Pareto optimality in which dominance is defined over full trajectories. Within this framework, Pareto traps emerge as locally non-dominated regions of trajectory space that nevertheless restrict access to globally superior developmental paths under conservative local optimization. To characterize the rigidity of such constraints, we define the Trap Escape Difficulty Index (TEDI), a composite geometric measure capturing escape distance, structural constraints, and behavioral inertia. We show that dynamic intelligence ceilings arise as inevitable geometric consequences of trajectory-level dominance, independent of learning progress or architectural scale. We further introduce a formal taxonomy of Pareto traps and illustrate the resulting trajectory-level divergence using a minimal agent-environment model. Together, these results shift the locus of intelligence from terminal performance to optimization geometry, providing a principled framework for diagnosing and overcoming long-horizon developmental constraints in adaptive systems.

Detecting text generated by large language models (LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rely on text-level features, leading to imprecise detection ability. In this paper, we propose a simple but effective and practical LLM-generated text detection method, VaryBalance. The core of VaryBalance is that, compared to LLM-generated texts, there is a greater difference between human texts and their rewritten version via LLMs. Leveraging this observation, VaryBalance quantifies this through mean standard deviation and distinguishes human texts and LLM-generated texts. Comprehensive experiments demonstrated that VaryBalance outperforms the state-of-the-art detectors, i.e., Binoculars, by up to 34.3\% in terms of AUROC, and maintains robustness against multiple generating models and languages.

The main issue with most evaluation schemes today is their "static" nature: the same problems are reused repeatedly, allowing for memorization, format exploitation, and eventual saturation. To measure genuine AI progress, we need evaluation that is robust by construction, not by post-hoc detection. In response, we propose VeRA (Verified Reasoning Data Augmentation), a framework that converts benchmark problems into executable specifications, comprising (i) a natural language template with placeholder slots, (ii) a coherent generator that samples valid configurations, and (iii) a deterministic verifier that validates parameters and calculates the corresponding correct answers for each configuration. From a single seed problem, VeRA automatically creates unlimited verified variants with reliable labels at near-zero marginal cost without human involvement. VeRA operates in two complementary modes. VeRA-E (equivalent) rewrites problems while keeping the underlying logic intact, useful for detecting memorization versus genuine reasoning. VeRA-H (hardened) systematically increases complexity while remaining verifiable, enabling reliable creation and labelling of fresh difficult tasks at the boundary of intelligence. Evaluating 16 frontier models with VeRA, we find: (i) VeRA-E improves evaluation quality and reveals contamination patterns. (ii) VeRA-H enables human-free generation of hard tasks with reliable labels. (iii) VeRA establishes verified benchmarks as a general paradigm. VeRA reconceptualizes benchmarks from static objects used until exhausted, to executable specifications generating fresh, verified instances on demand, enhancing robustness and cost-effectiveness for evaluation. With VeRA, we envision that evaluation in any verifiable domain can scale indefinitely without sacrificing label integrity. To stimulate future research, we have open-sourced all code and datasets.

Large Language Models (LLMs) are increasingly deployed in interactive environments requiring strategic decision-making, yet systematic evaluation of these capabilities remains challenging. Existing benchmarks for LLMs primarily assess static reasoning through isolated tasks and fail to capture dynamic strategic abilities. Recent game-based evaluations employ LLM-vs-LLM tournaments that produce relative rankings dependent on transient model pools, incurring quadratic computational costs and lacking stable performance anchors for longitudinal tracking. The central challenge is establishing a scalable evaluation framework that measures LLM strategic reasoning against consistent, interpretable standards rather than volatile peer models. Here we show that anchoring LLM evaluation to fixed hierarchies of skill-calibrated game Artificial Intelligence (AI) enables linear-time absolute skill measurement with stable cross-temporal interpretability. Built on the Botzone platform's established competitive infrastructure, our BotzoneBench evaluates LLMs across eight diverse games spanning deterministic perfect-information board games to stochastic imperfect-information card games. Through systematic assessment of 177,047 state-action pairs from five flagship models, we reveal significant performance disparities and identify distinct strategic behaviors, with top-performing models achieving proficiency comparable to mid-to-high-tier specialized game AI in multiple domains. This anchored evaluation paradigm generalizes beyond games to any domain with well-defined skill hierarchies, establishing a scalable and reusable framework for assessing interactive AI capabilities.

Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine policy pricing. While AI offers substantial efficiency improvements, existing solutions lack comprehensive reasoning capabilities and internal mechanisms to ensure reliability within regulated, high-stakes environments. Full automation remains impractical and inadvisable in scenarios where human judgment and accountability are critical. This study presents a decision-negative, human-in-the-loop agentic system that incorporates an adversarial self-critique mechanism as a bounded safety architecture for regulated underwriting workflows. Within this system, a critic agent challenges the primary agent's conclusions prior to submitting recommendations to human reviewers. This internal system of checks and balances addresses a critical gap in AI safety for regulated workflows. Additionally, the research develops a formal taxonomy of failure modes to characterize potential errors by decision-negative agents. This taxonomy provides a structured framework for risk identification and risk management in high-stakes applications. Experimental evaluation using 500 expert-validated underwriting cases demonstrates that the adversarial critique mechanism reduces AI hallucination rates from 11.3% to 3.8% and increases decision accuracy from 92% to 96%. At the same time, the framework enforces strict human authority over all binding decisions by design. These findings indicate that adversarial self-critique supports safer AI deployment in regulated domains and offers a model for responsible integration where human oversight is indispensable.

We study language-in-the-loop control for multi-drone systems that execute evolving, high-level missions while retaining formal robustness guarantees at the physical layer. We propose a three-layer architecture in which (i) a human operator issues natural-language instructions, (ii) an LLM-based supervisor periodically interprets, verifies, and corrects the commanded task in the context of the latest state and target estimates, and (iii) a distributed inner-loop controller tracks the resulting reference using only local relative information. We derive a theoretical guarantee that characterizes tracking performance under bounded disturbances and piecewise-smooth references with discrete jumps induced by LLM updates. Overall, our results illustrate how centralized language-based task reasoning can be combined with distributed feedback control to achieve complex behaviors with provable robustness and stability.

Unstructured documents like PDFs contain valuable structured information, but downstream systems require this data in reliable, standardized formats. LLMs are increasingly deployed to automate this extraction, making accuracy and reliability paramount. However, progress is bottlenecked by two gaps. First, no end-to-end benchmark evaluates PDF-to-JSON extraction under enterprise-scale schema breadth. Second, no principled methodology captures the semantics of nested extraction, where fields demand different notions of correctness (exact match for identifiers, tolerance for quantities, semantic equivalence for names), arrays require alignment, and omission must be distinguished from hallucination. We address both gaps with ExtractBench, an open-source benchmark and evaluation framework for PDF-to-JSON structured extraction. The benchmark pairs 35 PDF documents with JSON Schemas and human-annotated gold labels across economically valuable domains, yielding 12,867 evaluatable fields spanning schema complexities from tens to hundreds of fields. The evaluation framework treats the schema as an executable specification: each field declares its scoring metric. Baseline evaluations reveal that frontier models (GPT-5/5.2, Gemini-3 Flash/Pro, Claude 4.5 Opus/Sonnet) remain unreliable on realistic schemas. Performance degrades sharply with schema breadth, culminating in 0% valid output on a 369-field financial reporting schema across all tested models. We release ExtractBench at https://github.com/ContextualAI/extract-bench.

Autonomous driving requires reasoning about interactions with surrounding traffic. A prevailing approach is large-scale imitation learning on expert driving datasets, aimed at generalizing across diverse real-world scenarios. For online trajectory generation, such methods must operate at real-time rates. Diffusion models require hundreds of denoising steps at inference, resulting in high latency. Consistency models mitigate this issue but rely on carefully tuned noise schedules to capture the multimodal action distributions common in autonomous driving. Adapting the schedule, typically requires expensive retraining. To address these limitations, we propose a framework based on conditional flow matching that jointly predicts future motions of surrounding agents and plans the ego trajectory in real time. We train a lightweight variance estimator that selects the number of inference steps online, removing the need for retraining to balance runtime and imitation learning performance. To further enhance ride quality, we introduce a trajectory post-processing step cast as a convex quadratic program, with negligible computational overhead. Trained on the Waymo Open Motion Dataset, the framework performs maneuvers such as lane changes, cruise control, and navigating unprotected left turns without requiring scenario-specific tuning. Our method maintains a 20 Hz update rate on an NVIDIA RTX 3070 GPU, making it suitable for online deployment. Compared to transformer, diffusion, and consistency model baselines, we achieve improved trajectory smoothness and better adherence to dynamic constraints. Experiment videos and code implementations can be found at https://flow-matching-self-driving.github.io/.

Pretraining Vision-Language-Action (VLA) policies on internet-scale video is appealing, yet current latent-action objectives often learn the wrong thing: they remain anchored to pixel variation rather than action-relevant state transitions, making them vulnerable to appearance bias, nuisance motion, and information leakage. We introduce VLA-JEPA, a JEPA-style pretraining framework that sidesteps these pitfalls by design. The key idea is leakage-free state prediction: a target encoder produces latent representations from future frames, while the student pathway sees only the current observation -- future information is used solely as supervision targets, never as input. By predicting in latent space rather than pixel space, VLA-JEPA learns dynamics abstractions that are robust to camera motion and irrelevant background changes. This yields a simple two-stage recipe -- JEPA pretraining followed by action-head fine-tuning -- without the multi-stage complexity of prior latent-action pipelines. Experiments on LIBERO, LIBERO-Plus, SimplerEnv and real-world manipulation tasks show that VLA-JEPA achieves consistent gains in generalization and robustness over existing methods.

Humanoid facial expression shadowing enables robots to realistically imitate human facial expressions in real time, which is critical for lifelike, facially expressive humanoid robots and affective human-robot interaction. Existing progress in humanoid facial expression imitation remains limited, often failing to achieve either real-time performance or realistic expressiveness due to offline video-based inference designs and insufficient ability to capture and transfer subtle expression details. To address these limitations, we present VividFace, a real-time and realistic facial expression shadowing system for humanoid robots. An optimized imitation framework X2CNet++ enhances expressiveness by fine-tuning the human-to-humanoid facial motion transfer module and introducing a feature-adaptation training strategy for better alignment across different image sources. Real-time shadowing is further enabled by a video-stream-compatible inference pipeline and a streamlined workflow based on asynchronous I/O for efficient communication across devices. VividFace produces vivid humanoid faces by mimicking human facial expressions within 0.05 seconds, while generalizing across diverse facial configurations. Extensive real-world demonstrations validate its practical utility. Videos are available at: https://lipzh5.github.io/VividFace/.

In partially known environments, robots must combine exploration to gather information with task planning for efficient execution. To address this challenge, we propose EPoG, an Exploration-based sequential manipulation Planning framework on Scene Graphs. EPoG integrates a graph-based global planner with a Large Language Model (LLM)-based situated local planner, continuously updating a belief graph using observations and LLM predictions to represent known and unknown objects. Action sequences are generated by computing graph edit operations between the goal and belief graphs, ordered by temporal dependencies and movement costs. This approach seamlessly combines exploration and sequential manipulation planning. In ablation studies across 46 realistic household scenes and 5 long-horizon daily object transportation tasks, EPoG achieved a success rate of 91.3%, reducing travel distance by 36.1% on average. Furthermore, a physical mobile manipulator successfully executed complex tasks in unknown and dynamic environments, demonstrating EPoG's potential for real-world applications.

Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding novel-view synthesis. Explicit 3D models, though structurally informative, suffer from inherent inaccuracies (e.g., depth ambiguity and inaccurate dynamics) which, when used as a strong constraint, override the powerful intrinsic 3D awareness of large-scale video generators. In this work, we revisit motion control from a 3D-aware perspective, advocating for an implicit, view-agnostic motion representation that naturally aligns with the generator's spatial priors rather than depending on externally reconstructed constraints. We introduce 3DiMo, which jointly trains a motion encoder with a pretrained video generator to distill driving frames into compact, view-agnostic motion tokens, injected semantically via cross-attention. To foster 3D awareness, we train with view-rich supervision (i.e., single-view, multi-view, and moving-camera videos), forcing motion consistency across diverse viewpoints. Additionally, we use auxiliary geometric supervision that leverages SMPL only for early initialization and is annealed to zero, enabling the model to transition from external 3D guidance to learning genuine 3D spatial motion understanding from the data and the generator's priors. Experiments confirm that 3DiMo faithfully reproduces driving motions with flexible, text-driven camera control, significantly surpassing existing methods in both motion fidelity and visual quality.

Machine learning is a powerful method of extracting meaning from data; unfortunately, current digital hardware is extremely energy-intensive. There is interest in an alternative analog computing implementation that could match the performance of traditional machine learning while being significantly more energy-efficient. However, it remains unclear how to train such analog computing systems while adhering to locality constraints imposed by the physical (as opposed to digital) nature of these systems. Local learning algorithms such as Equilibrium Propagation and Coupled Learning have been proposed to address this issue. In this paper, we develop an algorithm to exactly calculate gradients using a graph theoretic and analytical framework for Kirchhoff's laws. We also introduce Generalized Equilibrium Propagation, a framework encompassing a broad class of Hebbian learning algorithms, including Coupled Learning and Equilibrium Propagation, and show how our algorithm compares. We demonstrate our algorithm using numerical simulations and show that we can train resistor networks without the need for a replica or readout over all resistors, only at the output layer. We also show that under the analytical gradient approach, it is possible to update only a subset of the resistance values without a strong degradation in performance.

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this formulation includes the massive tail of contextually irrelevant tokens in the action space, which could distract the policy from focusing on decision-making among the truly reasonable tokens. In this work, we verify that valid reasoning paths could inherently concentrate within a low-rank subspace. Based on this insight, we introduce Reinforcement Learning with Promising Tokens (RLPT), a framework that mitigates the action space issue by decoupling strategic decision-making from token generation. Specifically, RLPT leverages the semantic priors of the base model to identify a dynamic set of promising tokens and constrains policy optimization exclusively to this refined subset via masking. Theoretical analysis and empirical results demonstrate that RLPT effectively reduces gradient variance, stabilizes the training process, and improves sample efficiency. Experiment results on math, coding, and telecom reasoning show that RLPT outperforms standard RL baselines and integrates effectively across various model sizes (4B and 8B) and RL algorithms (GRPO and DAPO).