Providing timely and accurate learning support in large-scale online coding courses is challenging, particularly in resource-constrained contexts. We present Kwame 2.0, a bilingual (English-French) generative AI teaching assistant built using retrieval-augmented generation and deployed in a human-in-the-loop forum within SuaCode, an introductory mobile-based coding course for learners across Africa. Kwame 2.0 retrieves relevant course materials and generates context-aware responses while encouraging human oversight and community participation. We deployed the system in a 15-month longitudinal study spanning 15 cohorts with 3,717 enrollments across 35 African countries. Evaluation using community feedback and expert ratings shows that Kwame 2.0 provided high-quality and timely support, achieving high accuracy on curriculum-related questions, while human facilitators and peers effectively mitigated errors, particularly for administrative queries. Our findings demonstrate that human-in-the-loop generative AI systems can combine the scalability and speed of AI with the reliability of human support, offering an effective approach to learning assistance for underrepresented populations in resource-constrained settings at scale.

Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a capability where current vision-language models (VLMs) remain limited. We introduce ChartNet, a high-quality, million-scale multimodal dataset designed to advance chart interpretation and reasoning. ChartNet leverages a novel code-guided synthesis pipeline to generate 1.5 million diverse chart samples spanning 24 chart types and 6 plotting libraries. Each sample consists of five aligned components: plotting code, rendered chart image, data table, natural language summary, and question-answering with reasoning, providing fine-grained cross-modal alignment. To capture the full spectrum of chart comprehension, ChartNet additionally includes specialized subsets encompassing human annotated data, real-world data, safety, and grounding. Moreover, a rigorous quality-filtering pipeline ensures visual fidelity, semantic accuracy, and diversity across chart representations. Fine-tuning on ChartNet consistently improves results across benchmarks, demonstrating its utility as large-scale supervision for multimodal models. As the largest open-source dataset of its kind, ChartNet aims to support the development of foundation models with robust and generalizable capabilities for data visualization understanding. The dataset is publicly available at https://huggingface.co/datasets/ibm-granite/ChartNet

Wireless bioelectronic interfaces are increasingly used to control tissue-engineered biohybrid robotic systems. However, a unifying engineering framework linking device design to system-level control remains underdeveloped. Here, we propose that wireless control in biohybrid robotics can be formulated as a coupled co-design problem of integrating signal delivery, spatial selectivity, scalability, and interface stability. We analyze three representative control strategies, wireless electrical stimulation, wireless optoelectronic stimulation, and neuromuscular integration, which operates within a distinct regime with characteristic trade-offs. Across these modalities, the tissue-device interface emerges as a key constraint, governing the interplay between electromagnetic coupling, circuit performance, and biomechanical response. Based on this framework, we outline practical design principles spanning electromagnetic field distribution, circuit architecture, and actuator mechanics. We further propose a transition from open-loop stimulation to closed-loop biohybrid autonomy enabled by organoid-integrated bioelectronics and bidirectional microelectrode interfaces. This work establishes a system-level perspective on wireless bioelectronic control and provides design guidelines for developing stable, scalable, and autonomous biohybrid robotic systems.

Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors semantic plausibility, whereas OCR requires outputs that are visually grounded and geometrically verifiable. This mismatch produces severe errors, especially over-generation and unsupported substitutions, creating deployment risk even when benchmark accuracy remains high. We therefore formulate frozen VLM OCR as a selective accept/abstain problem and propose a model-agnostic Geometric Risk Controller. The controller probes multiple structured views of the same input, applies lightweight structural screening, and accepts a transcription only when cross-view consensus and stability satisfy predefined criteria, yielding a small family of operating points. Experiments on frozen VLM backbones and standard OCR benchmarks show consistent reductions in extreme-error risk and catastrophic over-generation at predictable coverage costs. Reliable deployment of generative OCR with frozen VLMs benefits from explicit system-level risk control rather than unconstrained generation.

In-context operator learning enables neural networks to infer solution operators from contextual examples without weight updates. While prior work has demonstrated the effectiveness of this paradigm in leveraging vast datasets, a systematic comparison against single-operator learning using identical training data has been absent. We address this gap through controlled experiments comparing in-context operator learning against classical operator learning (single-operator models trained without contextual examples), under the same training steps and dataset. To enable this investigation on real-world spatiotemporal systems, we propose GICON (Graph In-Context Operator Network), combining graph message passing for geometric generalization with example-aware positional encoding for cardinality generalization. Experiments on air quality prediction across two Chinese regions show that in-context operator learning outperforms classical operator learning on complex tasks, generalizing across spatial domains and scaling robustly from few training examples to 100 at inference.

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only output probabilities and hiding architecture, parameters, gradients, and training data. This opacity prevents meaningful auditing, bias detection, and failure analysis. Existing explanation methods assume white- or gray-box access or knowledge of the training distribution, making them unusable in these real-world settings. We introduce UNBOX, a framework for class-wise model dissection under fully data-free, gradient-free, and backpropagation-free constraints. UNBOX leverages Large Language Models and text-to-image diffusion models to recast activation maximization as a purely semantic search driven by output probabilities. The method produces human-interpretable text descriptors that maximally activate each class, revealing the concepts a model has implicitly learned, the training distribution it reflects, and potential sources of bias. We evaluate UNBOX on ImageNet-1K, Waterbirds, and CelebA through semantic fidelity tests, visual-feature correlation analyses and slice-discovery auditing. Despite operating under the strictest black-box constraints, UNBOX performs competitively with state-of-the-art white-box interpretability methods. This demonstrates that meaningful insight into a model's internal reasoning can be recovered without any internal access, enabling more trustworthy and accountable visual recognition systems.

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete and visually depictable, while safety concepts, like helpfulness, are abstract and lack visual referents. Inspired by the Self-Fulfilling mechanism underlying emergent misalignment, we propose Visual Self-Fulfilling Alignment (VSFA). VSFA fine-tunes vision-language models (VLMs) on neutral VQA tasks constructed around threat-related images, without any safety labels. Through repeated exposure to threat-related visual content, models internalize the implicit semantics of vigilance and caution, shaping safety-oriented personas. Experiments across multiple VLMs and safety benchmarks demonstrate that VSFA reduces the attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities. Our work extends the self-fulfilling mechanism from text to visual modalities, offering a label-free approach to VLMs alignment.

Scientists face significant visualization challenges as time-varying datasets grow in speed and volume, often requiring specialized infrastructure and expertise to handle massive datasets. Petascale climate models generated in NASA laboratories require a dedicated group of graphics and media experts and access to high-performance computing resources. Scientists may need to share scientific results with the community iteratively and quickly. However, the time-consuming trial-and-error process incurs significant data transfer overhead and far exceeds the time and resources allocated for typical post-analysis visualization tasks, disrupting the production workflow. Our paper introduces a user-friendly framework for creating 3D animations of petascale, time-varying data on a commodity workstation. Our contributions: (i) Generalized Animation Descriptor (GAD) with a keyframe-based adaptable abstraction for animation, (ii) efficient data access from cloud-hosted repositories to reduce data management overhead, (iii) tailored rendering system, and (iv) an LLM-assisted conversational interface as a scripting module to allow domain scientists with no visualization expertise to create animations of their region of interest. We demonstrate the framework's effectiveness with two case studies: first, by generating animations in which sampling criteria are specified based on prior knowledge, and second, by generating AI-assisted animations in which sampling parameters are derived from natural-language user prompts. In all cases, we use large-scale NASA climate-oceanographic datasets that exceed 1PB in size yet achieve a fast turnaround time of 1 minute to 2 hours. Users can generate a rough draft of the animation within minutes, then seamlessly incorporate as much high-resolution data as needed for the final version.

Purpose: This study evaluates the quality of commercial large language model (LLM) machine translation (MT) for Ancient Greek technical prose and benchmarks standard automated MT evaluation metrics against expert human judgment. Design: We evaluated 60 translations by three LLMs (ChatGPT, Claude, Gemini) of 20 paragraph-length passages from 2 works by the Greek physician Galen (c. 129-216 CE): an expository text with two published English translations and a pharmacological text never before translated. Quality was assessed using seven automated metrics and systematic reference-free human evaluation via a modified Multidimensional Quality Metrics (MQM) framework applied by domain specialists. Findings: On the translated expository text, LLMs achieved high quality (mean MQM score 95.2/100). On the untranslated pharmacological text, quality was lower (79.9/100) but bimodally distributed: two passages with extreme terminological density produced catastrophic failures, while remaining passages scored within 4 points of the expository text. Terminology rarity, operationalized via corpus frequency, emerged as the dominant predictor of failure (r = -.97). Automated metrics showed moderate correlation with human judgment only on texts with wide quality variance; no metric discriminated among high-quality translations. Originality: This is the first systematic, reference-free expert human evaluation of LLM translation for any ancient language and the first study identifying textual properties predictive of translation failure.

This paper presents a new unified approach to semantic segmentation in both images and videos by using language modeling to output the masks as sequences of discrete tokens. We use run length encoding (RLE) to discretize the segmentation masks, and adapt the Pix2Seq framework to learn autoregressive models to output these tokens. We propose novel tokenization strategies to compress the lengths of the token sequences to make it practicable to extend this approach to videos. We also show how instance information can be incorporated into the tokenization process to perform panoptic segmentation. We evaluate our models on two domain-specific datasets to demonstrate their competitiveness with the state of the art in certain scenarios, in spite of being severely bottlenecked by our limited computational resources. We supplement these analyses by proposing several promising approaches to foster future competitiveness in general-purpose applications, and facilitate this by making our code and models publicly available.

Scaling multimodal alignment between video and audio is challenging, particularly due to limited data and the mismatch between text descriptions and frame-level video information. In this work, we tackle the scaling challenge in multimodal-to-audio generation, examining whether models trained on short instances can generalize to longer ones during testing. To tackle this challenge, we present multimodal hierarchical networks so-called MMHNet, an enhanced extension of state-of-the-art video-to-audio models. Our approach integrates a hierarchical method and non-causal Mamba to support long-form audio generation. Our proposed method significantly improves long audio generation up to more than 5 minutes. We also prove that training short and testing long is possible in the video-to-audio generation tasks without training on the longer durations. We show in our experiments that our proposed method could achieve remarkable results on long-video to audio benchmarks, beating prior works in video-to-audio tasks. Moreover, we showcase our model capability in generating more than 5 minutes, while prior video-to-audio methods fall short in generating with long durations.

Contextuality is a central feature of quantum theory, traditionally understood as the impossibility of reproducing quantum measurement statistics using noncontextual ontological models. We study classical ontological descriptions in which a fixed subsystem-level ontic state space is reused across multiple interventions. Our main result is an information-theoretic obstruction: whenever a classical single-state model reproduces operational statistics using an auxiliary contextual register, the required contextual information is lower-bounded by the conditional mutual information $I(C;O\mid λ)$ between intervention $C$ and outcome $O$ conditioned on the subsystem ontic state $λ$. The mathematical inequality itself is elementary, but its interpretive significance is structural: under shared-state reuse, contextual distinctions need not be fully internalized within the subsystem ontic state alone. We provide a constructive illustration of this point and clarify how the issue should be understood as a limitation of subsystem-level classical representation, rather than as a dualism about physical reality. We further discuss how this perspective relates to ontological models and to contextuality in quantum foundations.

Independent indoor mobility remains a critical challenge for individuals with visual impairments, largely due to the limited capability of existing assistive systems in detecting fine-grained hazardous objects such as chairs, tables, and small obstacles. These perceptual blind zones substantially increase the risk of collision in unfamiliar environments. To bridge the gap between monocular 3D vision research and practical assistive deployment, this paper proposes an Adaptive Multi-scale Attention Aggregation (AMAA) framework for monocular 3D semantic scene completion using only a wearable RGB camera. The proposed framework addresses two major limitations in 2D-to-3D feature lifting: noise diffusion during back-projection and structural instability in multi-scale fusion. A parallel channel--spatial attention mechanism is introduced to recalibrate lifted features along semantic and geometric dimensions, while a hierarchical adaptive gating strategy regulates cross-scale information flow to preserve fine-grained structural details. Experiments on the NYUv2 benchmark demonstrate that AMAA achieves an overall mIoU of 27.88%. Crucially, it yields significant relative improvements of 16.9% for small objects and 10.4% for tables over the MonoScene baseline. Furthermore, a wearable prototype based on an NVIDIA Jetson Orin NX and a ZED~2i camera validates stable real-time performance in indoor environments, demonstrating the feasibility of deploying monocular 3D scene completion for assistive navigation.

Securing petroleum infrastructure requires balancing autonomous system efficiency with human judgment for threat escalation, a challenge unaddressed by classical facility location models assuming homogeneous resources. This paper formulates the Human-Robot Co-Dispatch Facility Location Problem (HRCD-FLP), a capacitated facility location variant incorporating tiered infrastructure criticality, human-robot supervision ratio constraints, and minimum utilization requirements. We evaluate command center selection across three technology maturity scenarios. Results show transitioning from conservative (1:3 human-robot supervision) to future autonomous operations (1:10) yields significant cost reduction while maintaining complete critical infrastructure coverage. For small problems, exact methods dominate in both cost and computation time; for larger problems, the proposed heuristic achieves feasible solutions in under 3 minutes with approximately 14% optimality gap where comparison is possible. From systems perspective, our work demonstrate that optimized planning for human-robot teaming is key to achieve both cost-effective and mission-reliable deployments.

Hospital administration departments handle a wide range of operational tasks and, in large hospitals, process over 10,000 requests per day, driving growing interest in LLM-based automation. However, prior work has focused primarily on patient-physician interactions or isolated administrative subtasks, failing to capture the complexity of real administrative workflows. To address this gap, we propose H-AdminSim, a comprehensive simulation framework that combines realistic data generation with multi-agent-based simulation of hospital administrative workflows. These tasks are quantitatively evaluated using detailed rubrics, enabling systematic comparison of LLMs. Through FHIR integration, H-AdminSim provides a unified and interoperable environment for testing administrative workflows across heterogeneous hospital settings, serving as a standardized testbed for assessing the feasibility and performance of LLM-driven administrative automation.

While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performance collapse in realistic, in-the-wild scenarios. In this work, we demonstrate that simplicity prevails over complex architectural designs. A simple linear classifier trained on the frozen features of modern Vision Foundation Models , including Perception Encoder, MetaCLIP 2, and DINOv3, establishes a new state-of-the-art. Through a comprehensive evaluation spanning traditional benchmarks, unseen generators, and challenging in-the-wild distributions, we show that this baseline not only matches specialized detectors on standard benchmarks but also decisively outperforms them on in-the-wild datasets, boosting accuracy by striking margins of over 30\%. We posit that this superior capability is an emergent property driven by the massive scale of pre-training data containing synthetic content. We trace the source of this capability to two distinct manifestations of data exposure: Vision-Language Models internalize an explicit semantic concept of forgery, while Self-Supervised Learning models implicitly acquire discriminative forensic features from the pretraining data. However, we also reveal persistent limitations: these models suffer from performance degradation under recapture and transmission, remain blind to VAE reconstruction and localized editing. We conclude by advocating for a paradigm shift in AI forensics, moving from overfitting on static benchmarks to harnessing the evolving world knowledge of foundation models for real-world reliability.

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion of the parameters, while only marginally impacting performance. This suggests that the computation is not uniformly distributed across the parameters. We introduce here a technique to systematically quantify computation density in LLMs. In particular, we design a density estimator drawing on mechanistic interpretability. We experimentally test our estimator and find that: (1) contrary to what has been often assumed, LLM processing generally involves dense computation; (2) computation density is dynamic, in the sense that models shift between sparse and dense processing regimes depending on the input; (3) per-input density is significantly correlated across LLMs, suggesting that the same inputs trigger either low or high density. Investigating the factors influencing density, we observe that predicting rarer tokens requires higher density, and increasing context length often decreases the density. We believe that our computation density estimator will contribute to a better understanding of the processing at work in LLMs, challenging their symbolic interpretation.

Current mobile manipulation research predominantly follows an instruction-driven paradigm, where agents rely on predefined textual commands to execute tasks. However, this setting confines agents to a passive role, limiting their autonomy and ability to react to dynamic environmental events. To address these limitations, we introduce sound-triggered mobile manipulation, where agents must actively perceive and interact with sound-emitting objects without explicit action instructions. To support these tasks, we develop Habitat-Echo, a data platform that integrates acoustic rendering with physical interaction. We further propose a baseline comprising a high-level task planner and low-level policy models to complete these tasks. Extensive experiments show that the proposed baseline empowers agents to actively detect and respond to auditory events, eliminating the need for case-by-case instructions. Notably, in the challenging dual-source scenario, the agent successfully isolates the primary source from overlapping acoustic interference to execute the first interaction, and subsequently proceeds to manipulate the secondary object, verifying the robustness of the baseline.

Large Language Models usually put more emphasis on accuracy and therefore, will guess even when not certain about the prediction, which is especially severe when fine-tuned on small datasets due to the inherent tendency toward miscalibration. In this work, we introduce Bayesian-LoRA, which reformulates the deterministic LoRA update as a probabilistic low-rank representation inspired by Sparse Gaussian Processes. We identify a structural isomorphism between LoRA's factorization and Kronecker-factored SGP posteriors, and show that LoRA emerges as a limiting case when posterior uncertainty collapses. We conduct extensive experiments on various LLM architectures across commonsense reasoning benchmarks. With only approximately 0.42M additional parameters and ${\approx}1.2{\times}$ training cost relative to standard LoRA, Bayesian-LoRA significantly improves calibration across models up to 30B, achieving up to 84% ECE reduction and 76% NLL reduction while maintaining competitive accuracy for both in-distribution and out-of-distribution (OoD) evaluations.

Sewing patterns define the structural foundation of garments and are essential for applications such as fashion design, fabrication, and physical simulation. Despite progress in automated pattern generation, accurately modeling sewing patterns remains difficult due to the broad variability in panel geometry and seam arrangements. In this work, we introduce a sewing pattern modeling method based on an implicit representation. We represent each panel using a signed distance field that defines its boundary and an unsigned distance field that identifies seam endpoints, and encode these fields into a continuous latent space that enables differentiable meshing. A latent flow matching model learns distributions over panel combinations in this representation, and a stitching prediction module recovers seam relations from extracted edge segments. This formulation allows accurate modeling and generation of sewing patterns with complex structures. We further show that it can be used to estimate sewing patterns from images with improved accuracy relative to existing approaches, and supports applications such as pattern completion and refitting, providing a practical tool for digital fashion design.

Existing cultural commonsense benchmarks treat nations as monolithic, assuming uniform practices within national boundaries. But does cultural commonsense hold uniformly within a nation, or does it vary at the sub-national level? We introduce Indica, the first benchmark designed to test LLMs' ability to address this question, focusing on India - a nation of 28 states, 8 union territories, and 22 official languages. We collect human-annotated answers from five Indian regions (North, South, East, West, and Central) across 515 questions spanning 8 domains of everyday life, yielding 1,630 region-specific question-answer pairs. Strikingly, only 39.4% of questions elicit agreement across all five regions, demonstrating that cultural commonsense in India is predominantly regional, not national. We evaluate eight state-of-the-art LLMs and find two critical gaps: models achieve only 13.4%-20.9% accuracy on region-specific questions, and they exhibit geographic bias, over-selecting Central and North India as the "default" (selected 30-40% more often than expected) while under-representing East and West. Beyond India, our methodology provides a generalizable framework for evaluating cultural commonsense in any culturally heterogeneous nation, from question design grounded in anthropological taxonomy, to regional data collection, to bias measurement.

The rapid expansion of research across machine learning, vision, and language has produced a volume of publications that is increasingly difficult to synthesize. Traditional bibliometric tools rely mainly on metadata and offer limited visibility into the semantic content of papers, making it hard to track how research themes evolve over time or how different areas influence one another.To obtain a clearer picture of recent developments, we compile a unified corpus of more than 100,000 papers from 22 major conferences between 2020 and 2025 and construct a multidimensional profiling pipeline to organize and analyze their textual content. By combining topic clustering, LLM-assisted parsing, and structured retrieval, we derive a comprehensive representation of research activity that supports the study of topic lifecycles, methodological transitions, dataset and model usage patterns, and institutional research directions.Our analysis highlights several notable shifts, including the growth of safety, multimodal reasoning, and agent-oriented studies, as well as the gradual stabilization of areas such as neural machine translation and graph-based methods. These findings provide an evidence-based view of how AI research is evolving and offer a resource for understanding broader trends and identifying emerging directions.

Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the context-dependent user intent evolves across interactions, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Existing studies usually follow static rewrite, retrieve, and generate pipelines, which optimize different procedures separately and overlook the mixed-initiative action optimization simultaneously. Although the recent developments in deep search agents demonstrate the effectiveness in jointly optimizing retrieval and generation via reasoning, these approaches focus on single-turn scenarios, which might lack the ability to handle multi-turn interactions. We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training with tailored rewards towards evolving user goals. The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods by surpassing several existing strong baselines.

Chain-of-Thought reasoning has significantly enhanced the problem-solving capabilities of Large Language Models. Unfortunately, current models generate reasoning steps sequentially without foresight, often becoming trapped in suboptimal reasoning paths with redundant steps. In contrast, we introduce Neural Chain-of-Thought Search (NCoTS), a framework that reformulates reasoning as a dynamic search for the optimal thinking strategy. By quantitatively characterizing the solution space, we reveal the existence of sparse superior reasoning paths that are simultaneously more accurate and concise than standard outputs. Our method actively navigates towards these paths by evaluating candidate reasoning operators using a dual-factor heuristic that optimizes for both correctness and computational cost. Consequently, NCoTS achieves a Pareto improvement across diverse reasoning benchmarks, boosting accuracy by over 3.5% while reducing generation length by over 22%. Our code and data are available at https://github.com/MilkThink-Lab/Neural-CoT-Search.

Spoken conversational systems require more than accurate speech generation to have human-like conversations: to feel natural and engaging, they must produce conversational behaviour that adapts dynamically to the context. Current spoken conversational systems, however, rarely allow such customization, limiting their naturalness and usability. In this work, we present the first open, instruction-following full-duplex conversational speech model that can be trained efficiently under typical academic resource constraints. By keeping the audio encoder frozen and finetuning only the language model, our model requires just 2,000 hours of data, without relying on large-scale pretraining or multi-stage optimization. The model can follow explicit instructions to control speaker voice, conversation topic, conversational behaviour (e.g., backchanneling and interruptions), and dialogue initiation. We propose a single-stage training protocol and systematically analyze design choices. Both the model and training code is released to enable reproducible research on controllable full-duplex speech systems.

Multi-step reasoning tasks like mathematical problem solving are vulnerable to cascading failures, where a single incorrect step leads to complete solution breakdown. Current LLM routing methods assign entire queries to one model, treating all reasoning steps as equal. We propose TRIM (Targeted routing in multi-step reasoning tasks), which routes only critical steps$\unicode{x2013}$those likely to derail the solution$\unicode{x2013}$to larger models while letting smaller models handle routine continuations. Our key insight is that targeted step-level interventions can fundamentally transform inference efficiency by confining expensive calls to precisely those steps where stronger models prevent cascading errors. TRIM operates at the step-level: it uses process reward models to identify erroneous steps and makes routing decisions based on step-level uncertainty and budget constraints. We develop several routing strategies within TRIM, ranging from a simple threshold-based policy to more expressive policies that reason about long-horizon accuracy-cost trade-offs and uncertainty in step-level correctness estimates. On MATH-500, even the simplest thresholding strategy surpasses prior routing methods with 5x higher cost efficiency, while more advanced policies match the strong, expensive model's performance using 80% fewer expensive model tokens. On harder benchmarks such as AIME, TRIM achieves up to 6x higher cost efficiency. All methods generalize effectively across math reasoning tasks, demonstrating that step-level difficulty represents fundamental characteristics of reasoning.

Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthfulness, yet the origins and mechanisms of these signals remain unclear. In this paper, we demonstrate that truthfulness cues arise from two distinct information pathways: (1) a Question-Anchored pathway that depends on question-answer information flow, and (2) an Answer-Anchored pathway that derives self-contained evidence from the generated answer itself. First, we validate and disentangle these pathways through attention knockout and token patching. Afterwards, we uncover notable and intriguing properties of these two mechanisms. Further experiments reveal that (1) the two mechanisms are closely associated with LLM knowledge boundaries; and (2) internal representations are aware of their distinctions. Finally, building on these insightful findings, two applications are proposed to enhance hallucination detection performance. Overall, our work provides new insight into how LLMs internally encode truthfulness, offering directions for more reliable and self-aware generative systems.

We present Exposía, the first public dataset that connects writing and feedback in higher education, enabling research on educationally grounded computational approaches to teaching and evaluating academic writing. Exposía includes student research project proposals and peer and instructor feedback consisting of comments and free-text reviews. The dataset was collected in the "Introduction to Scientific Work" course of the Computer Science. Exposía reflects the multi-stage nature of the academic writing process that includes drafting, receiving feedback, and revising the writing based on the feedback received. Both the project proposals and peer feedback are accompanied by human assessment scores based on a fine-grained, pedagogically-grounded schema for writing and feedback assessment that we develop. We use Exposía to benchmark state-of-the-art large language models (LLMs) on two tasks: automated scoring of (1) the proposals and (2) the student reviews. We find that the two tasks benefit from different LLMs. Furthermore, closed-source models consistently outperform open-weight models, motivating further research on improving the performance of open-weight models preferred in classroom settings. Finally, we establish that a prompting strategy that scores multiple aspects of the writing together is the most effective, an important finding for classroom deployment.

Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thinking approaches often lead to overthinking, where models produce excessively verbose responses even for simple queries, resulting in test-time inefficiency and even degraded accuracy. Prior work has attempted to mitigate this issue via adaptive reasoning strategies, but these methods largely overlook a fundamental bottleneck: visual perception failures. We argue that stable reasoning critically depends on low-level visual grounding, and that reasoning errors often originate from imperfect perception rather than insufficient deliberation. To address this limitation, we propose Gated Perception-Reasoning Optimization (GPRO), a meta-reasoning controller that dynamically routes computation among three decision paths at each generation step: a lightweight fast path, a slow perception path for re-examining visual inputs, and a slow reasoning path for internal self-reflection. To learn this distinction, we derive large-scale failure attribution supervision from approximately 790k samples, using teacher models to distinguish perceptual hallucinations from reasoning errors. We then train the controller with multi-objective reinforcement learning to optimize the trade-off between task accuracy and computational cost under uncertainty. Experiments on five benchmarks demonstrate that GPRO substantially improves both accuracy and efficiency, outperforming recent slow-thinking methods while generating significantly shorter responses.

One of the most important queries in knowledge compilation is weighted model counting (WMC), which has been applied to probabilistic inference on various models, such as Bayesian networks. In practical situations on inference tasks, the model's parameters have uncertainty because they are often learned from data, and thus we want to compute the degree of uncertainty in the inference outcome. One possible approach is to regard the inference outcome as a random variable by introducing distributions for the parameters and evaluate the variance of the outcome. Unfortunately, the tractability of computing such a variance is hardly known. Motivated by this, we consider the problem of computing the variance of WMC and investigate this problem's tractability. First, we derive a polynomial time algorithm to evaluate the WMC variance when the input is given as a structured d-DNNF. Second, we prove the hardness of this problem for structured DNNFs, d-DNNFs, and FBDDs, which is intriguing because the latter two allow polynomial time WMC algorithms. Finally, we show an application that measures the uncertainty in the inference of Bayesian networks. We empirically show that our algorithm can evaluate the variance of the marginal probability on real-world Bayesian networks and analyze the impact of the variances of parameters on the variance of the marginal.