Achieving cultural alignment in Large Language Models (LLMs) increasingly depends on synthetic data generation. For such synthesis, the most vital initial step is seed curation; however, current methods lack quantifiable standards for selecting these seeds. Existing approaches rely on unscalable manual curation or bias-prone LLM extraction, treating cultural specificity as an abstract concept rather than a measurable signal. In this paper, we address this "quantification gap" by proposing C-Mining, an unsupervised framework that transforms the discovery of cultural seeds from a subjective selection process into a computable data mining formulation. Our approach exploits a novel geometric insight, leveraging the cross-lingual misalignment of cultural concepts within pre-trained embedding spaces as a quantifiable discovery signal. By systematically identifying these regions characterized by pronounced linguistic exclusivity and geometric isolation, while actively filtering out noise, C-Mining automatically extracts high-fidelity Culture Points (CPs) from raw multilingual corpora without reliance on human or LLM supervision, reducing preparation costs by more than 150-fold. We further leverage the mined knowledge to steer the synthesis of diverse instruction-tuning datasets. Extensive experiments demonstrate that this seed-centric approach significantly enhances cultural understanding and reasoning capabilities, achieving a +6.03 point improvement on CulturalBench-Hard and surpassing state-of-the-art baselines, providing a scalable, quantifiable solution for high-quality cultural data synthesis.

Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the first error, throughput degrades when draft and target diverge. Rather than rejecting draft tokens outright, we propose to reweight them. To this end, we introduce sequential Monte Carlo speculative decoding (SMC-SD), which replaces token-level rejection with importance-weighted resampling over a population of draft particles. SMC-SD is a principled approximate inference scheme that trades exactness for additional speed, while preserving theoretical bounds on its per-step approximation error. Because LLM inference is memory bandwidth-bound, the arithmetic needed to draft particles and to score them in parallel comes nearly for free -- SMC-SD uses idle compute to turn verification into a vectorized, fixed-size operation with no rollback. Empirically, SMC-SD achieves 2.36x speed-up over speculative decoding and a 5.2x speed-up over autoregressive decoding, while remaining within 3% of the target model's accuracy on reasoning, instruction-following, and coding benchmarks.

Vision-Language-Action (VLA) models have demonstrated significant potential for embodied decision-making; however, their application in complex chemical laboratory automation remains restricted by limited long-horizon reasoning and the absence of persistent experience accumulation. Existing frameworks typically treat planning and execution as decoupled processes, often failing to consolidate successful strategies, which results in inefficient trial-and-error in multi-stage protocols. In this paper, we propose ChemBot, a dual-layer, closed-loop framework that integrates an autonomous AI agent with a progress-aware VLA model (Skill-VLA) for hierarchical task decomposition and execution. ChemBot utilizes a dual-layer memory architecture to consolidate successful trajectories into retrievable assets, while a Model Context Protocol (MCP) server facilitates efficient sub-agent and tool orchestration. To address the inherent limitations of VLA models, we further implement a future-state-based asynchronous inference mechanism to mitigate trajectory discontinuities. Extensive experiments on collaborative robots demonstrate that ChemBot achieves superior operational safety, precision, and task success rates compared to existing VLA baselines in complex, long-horizon chemical experimentation.

Reasoning segmentation has recently expanded from ground-level scenes to remote-sensing imagery, yet UAV data poses distinct challenges, including oblique viewpoints, ultra-high resolutions, and extreme scale variations. To address these issues, we formally define the UAV Reasoning Segmentation task and organize its semantic requirements into three dimensions: Spatial, Attribute, and Scene-level reasoning. Based on this formulation, we construct DRSeg, a large-scale benchmark for UAV reasoning segmentation, containing 10k high-resolution aerial images paired with Chain-of-Thought QA supervision across all three reasoning types. As a benchmark companion, we introduce PixDLM, a simple yet effective pixel-level multimodal language model that serves as a unified baseline for this task. Experiments on DRSeg establish strong baseline results and highlight the unique challenges of UAV reasoning segmentation, providing a solid foundation for future research.

Graph anomaly detection aims to identify irregular patterns in graph-structured data. Most unsupervised GNN-based methods rely on the homophily assumption that connected nodes share similar attributes. However, real-world graphs often exhibit attribute-level heterophily, where connected nodes have dissimilar attributes. Our analysis of attribute-level heterophily graphs reveals two phenomena indicating that current approaches are not practical for unsupervised graph anomaly detection: 1) attribute similarities between connected nodes show nearly identical distributions across different connected node pair types, and 2) anomalies cause consistent variation trends between the graph with and without anomalous edges in the low- and high-frequency components of the spectral energy distributions, while the mid-part exhibits more erratic variations. Based on these observations, we propose NK-GAD, a neighbor knowledge-enhanced unsupervised graph anomaly detection framework. NK-GAD integrates a joint encoder capturing both similar and dissimilar neighbor features, a neighbor reconstruction module modeling normal distributions, a center aggregation module refining node features, and dual decoders for reconstructing attributes and structures. Experiments on seven datasets show NK-GAD achieves an average 3.29\% AUC improvement.

Markerless 3D movement analysis from monocular video enables accessible biomechanical assessment in clinical and sports settings. However, most research-grade pipelines rely on GPU acceleration, limiting deployment on consumer-grade hardware and in low-resource environments. In this work, we optimize a monocular 3D biomechanics pipeline derived from the MonocularBiomechanics framework for efficient CPU-only execution. Through profiling-driven system optimization, including model initialization restructuring, elimination of disk I/O serialization, and improved CPU parallelization. Experiments on a consumer workstation (AMD Ryzen 7 9700X CPU) show a 2.47x increase in processing throughput and a 59.6\% reduction in total runtime, with initialization latency reduced by 4.6x. Despite these changes, biomechanical outputs remain highly consistent with the baseline implementation (mean joint-angle deviation 0.35$^\circ$, $r=0.998$). These results demonstrate that research-grade vision-based biomechanics pipelines can be deployed on commodity CPU hardware for scalable movement assessment.

Ultra-high-definition (UHD) image restoration poses unique challenges due to the high spatial resolution, diverse content, and fine-grained structures present in UHD images. To address these issues, we introduce a progressive spectral decomposition for the restoration process, decomposing it into three stages: zero-frequency \textbf{enhancement}, low-frequency \textbf{restoration}, and high-frequency \textbf{refinement}. Based on this formulation, we propose a novel framework, \textbf{ERR}, which integrates three cooperative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). The ZFE incorporates global priors to learn holistic mappings, the LFR reconstructs the main content by focusing on coarse-scale information, and the HFR adopts our proposed frequency-windowed Kolmogorov-Arnold Network (FW-KAN) to recover fine textures and intricate details for high-fidelity restoration. To further advance research in UHD image restoration, we also construct a large-scale, high-quality benchmark dataset, \textbf{LSUHDIR}, comprising 82{,}126 UHD images with diverse scenes and rich content. Our proposed methods demonstrate superior performance across a range of UHD image restoration tasks, and extensive ablation studies confirm the contribution and necessity of each module. Project page: https://github.com/NJU-PCALab/ERR.

Open-vocabulary remote sensing image segmentation (OVRSIS) remains underexplored due to fragmented datasets, limited training diversity, and the lack of evaluation benchmarks that reflect realistic geospatial application demands. Our previous \textit{OVRSISBenchV1} established an initial cross-dataset evaluation protocol, but its limited scope is insufficient for assessing realistic open-world generalization. To address this issue, we propose \textit{OVRSISBenchV2}, a large-scale and application-oriented benchmark for OVRSIS. We first construct \textbf{OVRSIS95K}, a balanced dataset of about 95K image--mask pairs covering 35 common semantic categories across diverse remote sensing scenes. Built upon OVRSIS95K and 10 downstream datasets, OVRSISBenchV2 contains 170K images and 128 categories, substantially expanding scene diversity, semantic coverage, and evaluation difficulty. Beyond standard open-vocabulary segmentation, it further includes downstream protocols for building extraction, road extraction, and flood detection, thereby better reflecting realistic geospatial application demands and complex deployment scenarios. We also propose \textbf{Pi-Seg}, a baseline for OVRSIS. Pi-Seg improves transferability through a \textbf{positive-incentive noise} mechanism, where learnable and semantically guided perturbations broaden the visual-text feature space during training. Extensive experiments on OVRSISBenchV1, OVRSISBenchV2, and downstream tasks show that Pi-Seg delivers strong and consistent results, particularly on the more challenging OVRSISBenchV2 benchmark. Our results highlight both the importance of realistic benchmark design and the effectiveness of perturbation-based transfer for OVRSIS. The code and datasets are available at \href{https://github.com/LiBingyu01/RSKT-Seg/tree/Pi-Seg}{LiBingyu01/RSKT-Seg/tree/Pi-Seg}.

Machine learning has achieved impressive performance in tomographic reconstruction, but supervised training requires paired measurements and ground-truth images that are often unavailable. This has motivated self-supervised approaches, which have primarily addressed denoising and, more recently, linear inverse problems. We address nonlinear inverse problems and introduce SPLIT (Self-supervised Partitioning for Learned Inversion in Nonlinear Tomography), a self-supervised machine-learning framework for reconstructing images from nonlinear, incomplete, and noisy projection data without any samples of ground-truth images. SPLIT enforces cross-partition consistency and measurement-domain fidelity while exploiting complementary information across multiple partitions. Our main theoretical result shows that, under mild conditions, the proposed self-supervised objective is equivalent to its supervised counterpart in expectation. We regularize training with an automatic stopping rule that halts optimization when a no-reference image-quality surrogate saturates. As a concrete application, we derive SPLIT variants for multispectral computed tomography. Experiments on sparse-view acquisitions demonstrate high reconstruction quality and robustness to noise, surpassing classical iterative reconstruction and recent self-supervised baselines.

Large Vision-Language Models (LVLMs) consistently require new arenas to guide their expanding boundaries, yet their capabilities with hypergraphs remain unexplored. In the real world, hypergraphs have significant practical applications in areas such as life sciences and social communities. Recent advancements in LVLMs have shown promise in understanding complex topologies, yet there remains a lack of a benchmark to delineate the capabilities of LVLMs with hypergraphs, leaving the boundaries of their abilities unclear. To fill this gap, in this paper, we introduce $\texttt{HyperGVL}$, the first benchmark to evaluate the proficiency of LVLMs in hypergraph understanding and reasoning. $\texttt{HyperGVL}$ provides a comprehensive assessment of 12 advanced LVLMs across 84,000 vision-language question-answering (QA) samples spanning 12 tasks, ranging from basic component counting to complex NP-hard problem reasoning. The involved hypergraphs contain multiscale synthetic structures and real-world citation and protein networks. Moreover, we examine the effects of 12 textual and visual hypergraph representations and introduce a generalizable router $\texttt{WiseHyGR}$ that improves LVLMs in hypergraph via learning adaptive representations. We believe that this work is a step forward in connecting hypergraphs with LVLMs.

Clinicians exploring oncology trial repositories often need ad-hoc, multi-constraint queries over biomarkers, endpoints, interventions, and time, yet writing SQL requires schema expertise. We demo FD-NL2SQL, a feedback-driven clinical NL2SQL assistant for SQLite-based oncology databases. Given a natural-language question, a schema-aware LLM decomposes it into predicate-level sub-questions, retrieves semantically similar expert-verified NL2SQL exemplars via sentence embeddings, and synthesizes executable SQL conditioned on the decomposition, retrieved exemplars, and schema, with post-processing validity checks. To improve with use, FD-NL2SQL incorporates two update signals: (i) clinician edits of generated SQL are approved and added to the exemplar bank; and (ii) lightweight logic-based SQL augmentation applies a single atomic mutation (e.g., operator or column change), retaining variants only if they return non-empty results. A second LLM generates the corresponding natural-language question and predicate decomposition for accepted variants, automatically expanding the exemplar bank without additional annotation. The demo interface exposes decomposition, retrieval, synthesis, and execution results to support interactive refinement and continuous improvement.

We present PINNACLE, an open-source computational framework for physics-informed neural networks (PINNs) that integrates modern training strategies, multi-GPU acceleration, and hybrid quantum-classical architectures within a unified modular workflow. The framework enables systematic evaluation of PINN performance across benchmark problems including 1D hyperbolic conservation laws, incompressible flows, and electromagnetic wave propagation. It supports a range of architectural and training enhancements, including Fourier feature embeddings, random weight factorization, strict boundary condition enforcement, adaptive loss balancing, curriculum training, and second-order optimization strategies, with extensibility to additional methods. We provide a comprehensive benchmark study quantifying the impact of these methods on convergence, accuracy, and computational cost, and analyze distributed data parallel scaling in terms of runtime and memory efficiency. In addition, we extend the framework to hybrid quantum-classical PINNs and derive a formal estimate for circuit-evaluation complexity under parameter-shift differentiation. Results highlight the sensitivity of PINNs to architectural and training choices, confirm their high computational cost relative to classical solvers, and identify regimes where hybrid quantum models offer improved parameter efficiency. PINNACLE provides a foundation for benchmarking physics-informed learning methods and guiding future developments through quantitative assessment of their trade-offs.

Continuum robots are well suited for navigating confined and fragile environments, such as vascular or endoluminal anatomy, where contact with surrounding structures is often unavoidable. While controlled contact can assist motion, unfavorable contact can degrade controllability, induce kinematic singularities, or introduce safety risks. We present a contact-aware planning approach that evaluates contact quality, penalizing hazardous interactions, while permitting benign contact. The planner produces kinematically feasible trajectories and contact-aware Jacobians which can be used for closed-loop control in hardware experiments. We validate the approach by testing the integrated system (planning, control, and mechanical design) on anatomical models from patient scans. The planner generates effective plans for three common anatomical environments, and, in all hardware trials, the continuum robot was able to reach the target while avoiding dangerous tip contact (100% success). Mean tracking errors were 1.9 +/- 0.5 mm, 1.2 +/- 0.1 mm, and 1.7 +/- 0.2 mm across the three different environments. Ablation studies showed that penalizing end-of-continuum-segment (ECS) contact improved manipulability and prevented hardware failures. Overall, this work enables reliable, contact-aware navigation in highly constrained environments.

VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images. However, existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability. To address this issue, we investigate Unsupervised Learning for VVI-ReID (USL-VVI-ReID), which learns identity-discriminative representations directly from unlabeled video tracklets. Directly extending image-based USL-VI-ReID methods to this setting with generic pretrained encoders leads to suboptimal performance. Such encoders suffer from weak identity discrimination and strong modality bias, resulting in severe intra-modality identity confusion and pronounced clustering granularity imbalance between visible and infrared modalities. These issues jointly degrade pseudo-label reliability and hinder effective cross-modality alignment. To address these challenges, we propose a Causal Bootstrapped Alignment (CBA) framework that explicitly exploits inherent video priors. First, we introduce Causal Intervention Warm-up (CIW), which performs sequence-level causal interventions by leveraging temporal identity consistency and cross-modality identity consistency to suppress modality- and motion-induced spurious correlations while preserving identity-relevant semantics, yielding cleaner representations for unsupervised clustering. Second, we propose Prototype-Guided Uncertainty Refinement (PGUR), which employs a coarse-to-fine alignment strategy to resolve cross-modality granularity mismatch, reorganizing under-clustered infrared representations under the guidance of reliable visible prototypes with uncertainty-aware supervision. Extensive experiments on the HITSZ-VCM and BUPTCampus benchmarks demonstrate that CBA significantly outperforms existing USL-VI-ReID methods when extended to the USL-VVI-ReID setting.

Cross-modal retrieval between food images and recipe texts is an important task with applications in nutritional management, dietary logging, and cooking assistance. Existing methods predominantly rely on dual-encoder architectures with separate image and text encoders, requiring complex alignment strategies and task-specific network designs to bridge the semantic gap between modalities. In this work, we propose SIMMER (Single Integrated Multimodal Model for Embedding Recipes), which applies Multimodal Large Language Model (MLLM)-based embedding models, specifically VLM2Vec, to this task, replacing the conventional dual-encoder paradigm with a single unified encoder that processes both food images and recipe texts. We design prompt templates tailored to the structured nature of recipes, which consist of a title, ingredients, and cooking instructions, enabling effective embedding generation by the MLLM. We further introduce a component-aware data augmentation strategy that trains the model on both complete and partial recipes, improving robustness to incomplete inputs. Experiments on the Recipe1M dataset demonstrate that SIMMER achieves state-of-the-art performance across both the 1k and 10k evaluation settings, substantially outperforming all prior methods. In particular, our best model improves the 1k image-to-recipe R@1 from 81.8\% to 87.5\% and the 10k image-to-recipe R@1 from 56.5\% to 65.5\% compared to the previous best method.

Language-aligned vision foundation models (VFMs) enable versatile visual understanding for always-on contextual AI, but their deployment on edge devices is hindered by strict latency and power constraints. We present AdaVFM, an adaptive framework for efficient on-device inference of language-aligned VFMs that dynamically adjusts computation based on scene context and task complexity. Our key insight is that the effect of model size reduction on performance is task-dependent in vision applications, motivating a runtime-adaptive execution strategy. AdaVFM integrates neural architecture search (NAS) into the language-aligned VFM backbone to enable lightweight subnet execution during runtime. A multimodal large language model (LLM) deployed on the cloud enables runtime control with a context-aware agent. This synergy allows efficient model adaptation under diverse conditions while maintaining strong accuracy. Extensive experiments on zero-shot classification and open-vocabulary segmentation demonstrate that AdaVFM achieves state-of-the-art accuracy-efficiency trade-offs, surpassing prior baselines by up to $7.9\%$ in acc@1 on IN1K and $5.2\%$ mIoU on ADE20K over the best models of comparable VFM sizes. For models with similar accuracy, AdaVFM further reduces average FLOPs by up to $77.9\%$.

Reconstructing the shape of continuum manipulators from sparse, noisy sensor data is a challenging task, owing to the infinite-dimensional nature of such systems. Existing approaches broadly trade off between parametric methods that yield compact state representations but lack probabilistic structure, and Cosserat rod inference on factor graphs, which provides principled uncertainty quantification at the cost of a state dimension that grows with the spatial discretization. This letter combines the strength of both paradigms by estimating the coefficients of a low-dimensional Geometric Variable Strain (GVS) parameterization within a factor graph framework. A novel kinematic factor, derived from the Magnus expansion of the strain field, encodes the closed-form rod geometry as a prior constraint linking the GVS strain coefficients to the backbone pose variables. The resulting formulation yields a compact state vector directly amenable to model-based control, while retaining the modularity, probabilistic treatment and computational efficiency of factor graph inference. The proposed method is evaluated in simulation on a 0.4 m long tendon-driven continuum robot under three measurement configurations, achieving mean position errors below 2 mm for all three scenarios and demonstrating a sixfold reduction in orientation error compared to a Gaussian process regression baseline when only position measurements are available.

We investigate Functional Majority Voting (FMV), a method based on functional consensus for code generation with Large Language Models, which identifies a representative solution from multiple generations using their runtime execution signatures on test inputs. We find that FMV is an effective test-time inference strategy, substantially boosting performance on LiveCodeBench without a large compute overhead. Furthermore, we extend the utility of functional consensus and apply it as an aggregation strategy for label-free Test-Time Reinforcement Learning. We demonstrate that this increases pass@1 on holdout tasks, but find no evidence of self-improvement beyond the base model's performance ceiling.

This paper proposes a novel method that incorporates empowerment when reasoning actions in reinforcement learning (RL), thereby achieving the flexibility of exploration-exploitation dilemma (EED). In previous methods, empowerment for promoting exploration has been provided as a bonus term to the task-specific reward function as an intrinsically-motivated RL. However, this approach introduces a delay until the policy that accounts for empowerment is learned, making it difficult to adjust the emphasis on exploration as needed. On the other hand, a trick devised for fine-tuning recent foundation models at reasoning, so-called best-of-N (BoN) sampling, allows for the implicit acquisition of modified policies without explicitly learning them. It is expected that applying this trick to exploration-promoting terms, such as empowerment, will enable more flexible adjustment of EED. Therefore, this paper investigates BoN sampling for empowerment. Furthermore, to adjust the degree of policy modification in a generalizable manner while maintaining computational cost, this paper proposes a novel BoN sampling method extended by Tsalis statistics. Through toy problems, the proposed method's cability to balance EED is verified. In addition, it is demonstrated that the proposed method improves RL performance to solve complex locomotion tasks.

Gaussian splatting has recently gained traction as a compelling map representation for SLAM systems, enabling dense and photo-realistic scene modeling. However, its application to monocular SLAM remains challenging due to the lack of reliable geometric cues from monocular input. Without geometric supervision, mapping or tracking could fall in local-minima, resulting in structural degeneracies and inaccuracies. To address this challenge, we propose GaussianFlow SLAM, a monocular 3DGS-SLAM that leverages optical flow as a geometry-aware cue to guide the optimization of both the scene structure and camera poses. By encouraging the projected motion of Gaussians, termed GaussianFlow, to align with the optical flow, our method introduces consistent structural cues to regularize both map reconstruction and pose estimation. Furthermore, we introduce normalized error-based densification and pruning modules to refine inactive and unstable Gaussians, thereby contributing to improved map quality and pose accuracy. Experiments conducted on public datasets demonstrate that our method achieves superior rendering quality and tracking accuracy compared with state-of-the-art algorithms. The source code is available at: https://github.com/url-kaist/gaussianflow-slam.

Latent diffusion models have emerged as powerful generative models in medical imaging, enabling the synthesis of high quality brain magnetic resonance imaging scans. In particular, predicting the evolution of a patients brain can aid in early intervention, prognosis, and treatment planning. In this study, we introduce CLIMB, Controllable Longitudinal brain Image generation via state space based latent diffusion model, an advanced framework for modeling temporal changes in brain structure. CLIMB is designed to model the structural evolution of the brain structure over time, utilizing a baseline MRI scan and its acquisition age as foundational inputs. Additionally, multiple conditional variables, including projected age, gender, disease status, genetic information, and brain structure volumes, are incorporated to enhance the temporal modeling of anatomical changes. Unlike existing LDM methods that rely on self attention modules, which effectively capture contextual information from input images but are computationally expensive, our approach leverages state space, a state space model architecture that substantially reduces computational overhead while preserving high-quality image synthesis. Furthermore, we introduce a Gaussian-aligned autoencoder that extracts latent representations conforming to prior distributions without the sampling noise inherent in conventional variational autoencoders. We train and evaluate our proposed model on the Alzheimers Disease Neuroimaging Initiative dataset, consisting of 6,306 MRI scans from 1,390 participants. By comparing generated images with real MRI scans, CLIMB achieves a structural similarity index of 0.9433, demonstrating notable improvements over existing methods.

Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO) enables input-space adaptation but faces high query costs and optimization challenges in the unsupervised TTA setting. We introduce BETA (Black-box Efficient Test-time Adaptation), a framework that addresses these limitations by employing a lightweight, local white-box steering model to create a tractable gradient pathway. Through a prediction harmonization technique combined with consistency regularization and prompt learning-oriented filtering, BETA enables stable adaptation with no additional API calls and negligible latency beyond standard inference. On ImageNet-C, BETA achieves a +7.1% accuracy gain on ViT-B/16 and +3.4% on CLIP, surpassing strong white-box and gray-box methods including TENT and TPT. On a commercial API, BETA achieves comparable performance to ZOO at 250x lower cost while maintaining real-time inference speed, establishing it as a practical and efficient solution for real-world black-box TTA.

AI design characteristics and human personality traits each impact the quality and outcomes of human-AI interactions. However, their relative and joint impacts are underexplored in imperfectly cooperative scenarios, where people and AI only have partially aligned goals and objectives. This study compares a purely simulated dataset comprising 2,000 simulations and a parallel human subjects experiment involving 290 human participants to investigate these effects across two scenario categories: (1) hiring negotiations between human job candidates and AI hiring agents; and (2) human-AI transactions wherein AI agents may conceal information to maximize internal goals. We examine user Extraversion and Agreeableness alongside AI design characteristics, including Adaptability, Expertise, and chain-of-thought Transparency. Our causal discovery analysis extends performance-focused evaluations by integrating scenario-based outcomes, communication analysis, and questionnaire measures. Results reveal divergences between purely simulated and human study datasets, and between scenario types. In simulation experiments, personality traits and AI attributes were comparatively influential. Yet, with actual human subjects, AI attributes -- particularly transparency -- were much more impactful. We discuss how these divergences vary across different interaction contexts, offering crucial insights for the future of human-centered AI agents.

Preference optimization is widely used to align Large Language Models (LLMs) with preference feedback. However, most existing methods train on a single positive-negative pair per prompt, discarding additional supervision available in preference datasets that typically contain multiple candidate responses. Motivated by this limitation, recent work explores group-wise preference optimization, which jointly contrasts multiple responses for the same prompt, but its empirical behavior and scalability remain underexplored due to the memory overhead of group-coupled objectives. In this work, we introduce a memory-efficient group-wise preference optimization algorithm that preserves gradients while decoupling samples during backpropagation, substantially reducing peak memory usage, which enables scalable training with larger group sizes. Across both offline and online alignment settings, we show that leveraging multiple responses consistently outperforms single-pair training. Furthermore, incorporating a negative log-likelihood (NLL) term on positive responses is critical for both performance gains and training stability.

Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (Gemini 3.1 Pro, Claude 4.6 Opus, GPT 5.4) corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely. Additional experiments reveal that agentic tool use does not improve performance on DELEGATE-52, and that degradation severity is exacerbated by document size, length of interaction, or presence of distractor files. Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors that silently corrupt documents, compounding over long interaction.

Large language models compress heterogeneous knowledge into a single parameter space, allowing facts from different domains to interfere during generation. We propose DALM, a Domain-Algebraic Language Model that replaces unconstrained token generation with structured denoising over a domain lattice. DALM follows a three-phase generation path: it first resolves domain uncertainty, then relation uncertainty, and finally concept uncertainty, so each stage operates under explicit algebraic constraints. The framework requires only three ingredients: a lattice of domains with computable meet, join, and implication; a typing function over relations that controls inheritance across domains; and a fiber partition that localizes knowledge to domain-specific subsets. Given these ingredients, DALM yields a three-phase encoder-decoder architecture in which generation is confined to a domain fiber, cross-domain contamination is structurally prevented in closed-vocabulary mode and auditably bounded in open-vocabulary mode, and a single query can produce a domain-indexed multi-perspective answer space. We instantiate the framework with the CDC knowledge representation system and outline training and evaluation on validated domain-annotated crystal libraries. DALM reframes language generation as algebraically constrained structured denoising rather than unconstrained decoding over a flat token space.

Existing research on large language models (LLMs) for automated code compliance has primarily focused on performance, treating the models as black boxes and overlooking how training decisions affect their interpretive behavior. This paper addresses this gap by employing a perturbation-based attribution analysis to compare the interpretive behaviors of LLMs across different fine-tuning strategies such as full fine-tuning (FFT), low-rank adaptation (LoRA) and quantized LoRA fine-tuning, as well as the impact of model scales which include varying LLM parameter sizes. Our results show that FFT produces attribution patterns that are statistically different and more focused than those from parameter-efficient fine-tuning methods. Furthermore, we found that as model scale increases, LLMs develop specific interpretive strategies such as prioritizing numerical constraints and rule identifiers in the building text, albeit with performance gains in semantic similarity of the generated and reference computer-processable rules plateauing for models larger than 7B. This paper provides crucial insights into the explainability of these models, taking a step toward building more transparent LLMs for critical, regulation-based tasks in the Architecture, Engineering, and Construction industry.

The integration of Large Language Models (LLMs) into scientific workflows presents exciting opportunities to accelerate biomedical discovery. However, the reactive nature of LLMs, which respond only when prompted, limits their effectiveness in collaborative settings that demand foresight and autonomous engagement. In this study, we introduce CoLabScience, a proactive LLM assistant designed to enhance biomedical collaboration between AI systems and human experts through timely, context-aware interventions. At the core of our method is PULI (Positive-Unlabeled Learning-to-Intervene), a novel framework trained with a reinforcement learning objective to determine when and how to intervene in streaming scientific discussions, by leveraging the team's project proposal and long- and short-term conversational memory. To support this work, we introduce BSDD (Biomedical Streaming Dialogue Dataset), a new benchmark of simulated research discussion dialogues with intervention points derived from PubMed articles. Experimental results show that PULI significantly outperforms existing baselines in both intervention precision and collaborative task utility, highlighting the potential of proactive LLMs as intelligent scientific assistants.

Predicting the relative value of any given chess piece in a position remains an open challenge, as a piece's contribution depends on its spatial relationships with every other piece on the board. We demonstrate that incorporating the state of the full chess board via latent position representations derived using a CNN-based autoencoder significantly improves accuracy for MLP-based piece value prediction architectures. Using a dataset of over 12 million piece-value pairs gathered from Grandmaster-level games, with ground-truth labels generated by Stockfish 17, our enhanced piece value predictor significantly outperforms context-independent MLP-based systems, reducing validation mean absolute error by 16% and predicting relative piece value within approximately 0.65 pawns. More generally, our findings suggest that encoding the full problem state as context provides useful inductive bias for predicting the contribution of any individual component.

Consider an auto-regressive model that produces outputs x (e.g., answers to questions, molecules) each of which can be summarized by an attribute vector y (e.g., helpfulness vs. harmlessness, or bio-availability vs. lipophilicity). An arbitrary reward function r(y) encodes tradeoffs between these properties. Typically, tilting the model's sampling distribution to increase this reward is done at training time via reinforcement learning. However, if the reward function changes, re-alignment requires re-training. In this paper, we show that a reward weighted classifier-free guidance (RCFG) can act as a policy improvement operator in this setting, approximating tilting the sampling distribution by the Q function. We apply RCFG to molecular generation, demonstrating that it can optimize novel reward functions at test time. Finally, we show that using RCFG as a teacher and distilling into the base policy to serve as a warm start significantly speeds up convergence for standard RL.