01A 1/R Law for Kurtosis Contrast in Balanced MixturesKurtosis-based Independent Component Analysis (ICA) weakens in wide, balanced mixtures. We prove a sharp redundancy law: for a standardized projection w...02Flow Matching is Adaptive to Manifold StructuresFlow matching has emerged as a simulation-free alternative to diffusion-based generative modeling, producing samples by solving an ODE whose time-depend...03LoBoost: Fast Model-Native Local Conformal Predictio...Gradient-boosted decision trees are among the strongest off-the-shelf predictors for tabular regression, but point predictions alone do not quantify unc...04Probing the Geometry of Diffusion Models with the St...Understanding the geometry of learned distributions is fundamental to improving and interpreting diffusion models, yet systematic tools for exploring th...05Sampling from Constrained Gibbs Measures: with Appli...This paper considers a non-standard problem of generating samples from a low-temperature Gibbs distribution with mph{constrained} support, when some o...06A Dataset is Worth 1 MBA dataset server must often distribute the same large payload to many clients, incurring massive communication costs. Since clients frequently operate o...07A Decision-Theoretic Formalisation of Steganography...Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms....08A Mixture-of-Experts Model for Multimodal Emotion Re...Emotion Recognition in Conversations (ERC) presents unique challenges, requiring models to capture the temporal flow of multi-turn dialogues and to effe...09A note on the area under the likelihood and the fake...Improper priors are not allowed for the computation of the Bayesian evidence $Z=p({f y})$ (a.k.a., marginal likelihood), since in this case $Z$ is not...10A Proper Scoring Rule for Virtual StainingGenerative virtual staining (VS) models for high-throughput screening (HTS) can provide an estimated posterior distribution of possible biological featu...11Affine-Scaled Attention: Towards Flexible and Stable...Transformer attention is typically implemented using softmax normalization, which enforces attention weights with unit sum normalization. While effectiv...12AgentDropoutV2: Optimizing Information Flow in Multi...While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual parti...13An automatic counting algorithm for the quantificati...Counting immunopositive cells on biological tissues generally requires either manual annotation or (when available) automatic rough systems, for scannin...14Assessing Deanonymization Risks with Stylometry-Assi...The rapid advancement of large language models (LLMs) has enabled powerful authorship inference capabilities, raising growing concerns about unintended...15Beyond NNGP: Large Deviations and Feature Learning i...We study wide Bayesian neural networks focusing on the rare but statistically dominant fluctuations that govern posterior concentration, beyond Gaussian...16Bitwise Systolic Array Architecture for Runtime-Reco...Neural network accelerators have been widely applied to edge devices for complex tasks like object tracking, image recognition, etc. Previous works have...17CiteLLM: An Agentic Platform for Trustworthy Scienti...Large language models (LLMs) have created new opportunities to enhance the efficiency of scholarly activities; however, challenges persist in the ethica...18Conformalized Neural Networks for Federated Uncertai...Federated learning (FL) faces challenges in uncertainty quantification (UQ). Without reliable UQ, FL systems risk deploying overconfident models at unde...19CXReasonAgent: Evidence-Grounded Diagnostic Reasonin...Chest X-ray plays a central role in thoracic diagnosis, and its interpretation inherently requires multi-step, evidence-grounded reasoning. However, lar...20Decentralized Ranking Aggregation: Gossip Algorithms...The concept of ranking aggregation plays a central role in preference analysis, and numerous algorithms for calculating median rankings, often originati...21Decomposing Private Image Generation via Coarse-to-F...Generative models trained on sensitive image datasets risk memorizing and reproducing individual training examples, making strong privacy guarantees ess...22Deep ensemble graph neural networks for probabilisti...Using advanced machine learning techniques, we developed a method for reconstructing precisely the arrival direction and energy of ultra-high-energy cos...23Differentiable Zero-One Loss via Hypersimplex Projec...Recent advances in machine learning have emphasized the integration of structured optimization components into end-to-end differentiable models, enablin...24Discourse-Aware Dual-Track Streaming Response for Lo...Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a...25Effective sample size approximations as entropy meas...In this work, we analyze alternative effective sample size (ESS) metrics for importance sampling algorithms, and discuss a possible extended range of ap...26Evaluating Stochasticity in Deep Research AgentsDeep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial de...27Evaluating Zero-Shot and One-Shot Adaptation of Smal...Leader-follower interaction is an important paradigm in human-robot interaction (HRI). Yet, assigning roles in real time remains challenging for resourc...28Fine-Tuning Without Forgetting In-Context Learning:...Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations....29FlashOptim: Optimizers for Memory Efficient TrainingStandard mixed-precision training of neural networks requires many bytes of accelerator memory for each model parameter. These bytes reflect not just th...30Frequency-Ordered Tokenization for Better Text Compr...We present frequency-ordered tokenization, a simple preprocessing technique that improves lossless text compression by exploiting the power-law frequenc...31From Shallow Bayesian Neural Networks to Gaussian Pr...In this work, we study scaling limits of shallow Bayesian neural networks (BNNs) via their connection to Gaussian processes (GPs), with an emphasis on s...32Generalized Rapid Action Value Estimation in Memory-...Generalized Rapid Action Value Estimation (GRAVE) has been shown to be a strong variant within the Monte-Carlo Tree Search (MCTS) family of algorithms f...33Global Interpretability via Automated Preprocessing:...Psychiatric questionnaires are highly context sensitive and often only weakly predict subsequent symptom severity, which makes the prognostic relationsh...34Inferential Mechanics Part 1: Causal Mechanistic The...Machine learning techniques are now routinely encountered in research laboratories across the globe. Impressive progress has been made through ML and AI...35InnerQ: Hardware-aware Tuning-free Quantization of K...Reducing the hardware footprint of large language models (LLMs) during decoding is critical for efficient long-sequence generation. A key bottleneck is...36Invariant Transformation and Resampling based Episte...An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained...37Kernel Integrated $R^2$: A Measure of DependenceWe introduce kernel integrated $R^2$, a new measure of statistical dependence that combines the local normalization principle of the recently introduced...38Large Multimodal Models as General In-Context Classi...Which multimodal model should we use for classification? Previous studies suggest that the answer lies in CLIP-like contrastive Vision-Language Models (...39LineGraph2Road: Structural Graph Reasoning on Line G...The accurate and automatic extraction of roads from satellite imagery is critical for applications in navigation and urban planning, significantly reduc...40LLM Novice Uplift on Dual-Use, In Silico Biology TasksLarge language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable hu...41Low-degree Lower bounds for clustering in moderate d...We study the fundamental problem of clustering $n$ points into $K$ groups drawn from a mixture of isotropic Gaussians in $\mathbb{R}^d$. Specifically, w...42Make It Hard to Hear, Easy to Learn: Long-Form Benga...Although Automatic Speech Recognition (ASR) in Bengali has seen significant progress, processing long-duration audio and performing robust speaker diari...43ManifoldGD: Training-Free Hierarchical Manifold Guid...In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compac...44Mean Estimation from Coarse Data: Characterizations...Coarse data arise when learners observe only partial information about samples; namely, a set containing the sample rather than its exact value. This oc...45MediX-R1: Open Ended Medical Reinforcement LearningWe introduce MediX-R1, an open-ended Reinforcement Learning (RL) framework for medical multimodal large language models (MLLMs) that enables clinically...46Modality Collapse as Mismatched Decoding: Informatio...Multimodal LLMs can process speech and images, but they cannot hear a speaker's voice or see an object's texture. We show this is not a failure of encod...47Model Agreement via AnchoringNumerous lines of aim to control $ extit{model disagreement}$ -- the extent to which two machine learning models disagree in their predictions. We adop...48MoDora: Tree-Based Semi-Structured Document Analysis...Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various and often irre...49MovieTeller: Tool-augmented Movie Synopsis with ID C...With the explosive growth of digital entertainment, automated video summarization has become indispensable for applications such as content indexing, pe...50MTRAG-UN: A Benchmark for Open Challenges in Multi-T...We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We...51Neural Operators Can Discover Functional ClustersOperator learning is reshaping scientific computing by amortizing inference across infinite families of problems. While neural operators (NOs) are incre...52ODEBrain: Continuous-Time EEG Graph for Modeling Dyn...Modeling neural population dynamics is crucial for foundational neuroscientific research and various clinical applications. Conventional latent variable...53ParamMem: Augmenting Language Agents with Parametric...Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent...54Partition Function Estimation under Bounded f-Diverg...We study the statistical complexity of estimating partition functions given sample access to a proposal distribution and an unnormalized density ratio f...55PGVMS: A Prompt-Guided Unified Framework for Virtual...Immunohistochemical (IHC) staining enables precise molecular profiling of protein expression, with over 200 clinically available antibody-based tests in...56Physics Informed Viscous Value RepresentationsOffline goal-conditioned reinforcement learning (GCRL) learns goal-conditioned policies from static pre-collected datasets. However, accurate value esti...57Plug-and-Play Diffusion Meets ADMM: Dual-Variable Co...Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generat...58PRIMA: Pre-training with Risk-integrated Image-Metad...Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as iso...59Quantity Convergence, Quality Divergence: Disentangl...While second language (L2) learners may acquire target syntactic word order, mapping this syntax onto appropriate prosodic structures remains a persiste...60Regular Fourier Features for Nonstationary Gaussian...Simulating a Gaussian process requires sampling from a high-dimensional Gaussian distribution, which scales cubically with the number of sample location...61Regularized Online RLHF with Generalized Bilinear Pr...We consider the problem of contextual online RLHF with general preferences, where the goal is to identify the Nash Equilibrium. We adopt the Generalized...62Retrieve and Segment: Are a Few Examples Enough to B...Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling s...63Risk-Aware World Model Predictive Control for Genera...With advances in imitation learning (IL) and large-scale driving datasets, end-to-end autonomous driving (E2E-AD) has made great progress recently. Curr...64Scale Can't Overcome Pragmatics: The Impact of Repor...The lack of reasoning capabilities in Vision-Language Models (VLMs) has remained at the forefront of research discourse. We posit that this behavior ste...65Scaling Search Relevance: Augmenting App Store Ranki...Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize re...66SeeThrough3D: Occlusion Aware 3D Control in Text-to-...We identify occlusion reasoning as a fundamental yet overlooked aspect for 3D layout-conditioned generation. It is essential for synthesizing partially...67Sensor Generalization for Adaptive Sensing in Event-...Bio-inspired event cameras have recently attracted significant research due to their asynchronous and low-latency capabilities. These features provide a...68Sharp Convergence Rates for Masked Diffusion ModelsDiscrete diffusion models have achieved strong empirical performance in text and other symbolic domains, with masked (absorbing-rate) variants emerging...69Skarimva: Skeleton-based Action Recognition is a Mul...Human action recognition plays an important role when developing intelligent interactions between humans and machines. While there is a lot of active re...70SOTAlign: Semi-Supervised Alignment of Unimodal Visi...The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the wor...71SPARTA: Scalable and Principled Benchmark of Tree-St...Real-world Table-Text question answering (QA) tasks require models that can reason across long text and source tables, traversing multiple hops and exec...72Spatio-Temporal Token Pruning for Efficient High-Res...Pure-vision GUI agents provide universal interaction capabilities but suffer from severe efficiency bottlenecks due to the massive spatiotemporal redund...73Takeuchi's Information Criteria as Generalization Me...Generalization measures have been studied extensively in the machine learning community to better characterize generalization gaps. However, establishin...74Tell Me What To Learn: Generalizing Neural Memory to...Modern machine learning models are deployed in diverse, non-stationary environments where they must continually adapt to new tasks and evolving knowledg...75The logic of KM belief update is contained in the lo...For each axiom of KM belief update we provide a corresponding axiom in a modal logic containing three modal operators: a unimodal belief operator $B$, a...76ThinkOmni: Lifting Textual Reasoning to Omni-modal S...Omni-modal reasoning is essential for intelligent systems to understand and draw inferences from diverse data sources. While existing omni-modal large l...77Toward Automatic Filling of Case Report Forms: A Cas...Case Report Forms (CRFs) collect data about patients and are at the core of well-established practices to conduct research in clinical settings. With th...78Toward Expert Investment Teams:A Multi-Agent LLM Sys...The advancement of large language models (LLMs) has accelerated the development of autonomous financial trading systems. While mainstream approaches dep...79Towards Long-Form Spatio-Temporal Video GroundingIn real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual...80Uncovering Physical Drivers of Dark Matter Halo Stru...Deep generative models (DGMs) compress high-dimensional data but often entangle distinct physical factors in their latent spaces. We present an auxiliar...81Understanding Usage and Engagement in AI-Powered Sci...AI-powered scientific research tools are rapidly being integrated into research workflows, yet the field lacks a clear lens into how researchers use the...82UniScale: Unified Scale-Aware 3D Reconstruction for...We present UniScale, a unified, scale-aware multi-view 3D reconstruction framework for robotic applications that flexibly integrates geometric priors th...83Unsupervised Continual Learning for Amortized Bayesi...Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers...84Utilizing LLMs for Industrial Process AutomationA growing number of publications address the best practices to use Large Language Models (LLMs) for software engineering in recent years. However, most...85VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at...We present a scalable 3D reconstruction model that addresses a critical limitation in offline feed-forward methods: their computational and memory requi...86Why Diffusion Language Models Struggle with Truly Pa...Diffusion Language Models (DLMs) are often advertised as enabling parallel token generation, yet practical fast DLMs frequently converge to left-to-righ...87Zeroth-Order Stackelberg Control in Combinatorial Co...We study Stackelberg (leader--follower) tuning of network parameters (tolls, capacities, incentives) in combinatorial congestion games, where selfish us...88A distributed semismooth Newton based augmented Lagr...This paper proposes a novel distributed semismooth Newton based augmented Lagrangian method for solving a class of optimization problems over networks,...89A Minimal Agent for Automated Theorem ProvingWe propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements...90A Mixed Diet Makes DINO An Omnivorous Vision EncoderPre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their feature representati...91A multimodal slice discovery framework for systemati...Despite advances in machine learning-based medical image classifiers, the safety and reliability of these systems remain major concerns in practical set...92A Novel Hierarchical Multi-Agent System for Payments...Large language model (LLM) agents, such as OpenAI's Operator and Claude's Computer Use, can automate workflows but unable to handle payment tasks. Exist...93A Variational Estimator for $L_p$ Calibration ErrorsCalibration - the problem of ensuring that predicted probabilities align with observed class frequencies - is a basic desideratum for reliable ML prediction.94Active Bipartite Ranking with Smooth Posterior Distr...In this article, bipartite ranking, a statistical learning problem involved in many applications and widely studied in the passive context, is approache...95Adaptive Combinatorial Experimental Design: Pareto O...In this paper, we provide the first investigation into adaptive combinatorial experimental design, focusing on the trade-off between regret minimization...96AgenticOCR: Parsing Only What You Need for Efficient...The expansion of retrieval-augmented generation (RAG) into multimodal domains has intensified the challenge for processing complex visual documents, suc...97An Efficient Unsupervised Federated Learning Approac...Federated learning (FL) is an effective paradigm for distributed environments such as the Internet of Things (IoT), where data from diverse devices with...98ArgLLM-App: An Interactive System for Argumentative...Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with...99ARGUS: Seeing the Influence of Narrative Features on...Can narratives make arguments more persuasive? And to this end, which narrative features matter most? Although stories are often seen as powerful tools...100Better Learning-Augmented Spanning Tree Algorithms v...We present improved learning-augmented algorithms for finding an approximate minimum spanning tree (MST) for points in an arbitrary metric space. Our wo...101BLISSNet: Deep Operator Learning for Fast and Accura...Reconstructing fluid flows from sparse sensor measurements is a fundamental challenge in science and engineering. Widely separated measurements and comp...102Chunk-wise Attention Transducers for Fast and Accura...We propose Chunk-wise Attention Transducer (CHAT), a novel extension to RNN-T models that processes audio in fixed-size chunks while employing cross-att...103CoME: Empowering Channel-of-Mobile-Experts with Info...Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, acti...104Comparing Classical and Quantum Variational Classifi...Quantum machine learning applies principles such as superposition and entanglement to data processing and optimization. Variational quantum models opera...105Compositional Generalization Requires Linear, Orthog...Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems. Although modern...106Controllable Reasoning Models Are Private ThinkersAI agents powered by reasoning models require access to sensitive user data. However, their reasoning traces are difficult to control, which can result...107Coverage-Aware Web Crawling for Domain-Specific Supp...Identifying the full landscape of small and medium-sized enterprises (SMEs) in specialized industry sectors is critical for supply-chain resilience, yet...108CUDA Agent: Large-Scale Agentic RL for High-Performa...GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong p...109DARE-bench: Evaluating Modeling and Instruction Fide...The fast-growing demands in using Large Language Models (LLMs) to tackle complex multi-step data science tasks create an emergent need for accurate benc...110Data Driven Optimization of GPU efficiency for Distr...Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving...111Do LLMs Benefit From Their Own Words?Multi-turn interactions with large language models typically retain the assistant's own past responses in the conversation history. In this work, we rev...112Efficient Discovery of Approximate Causal Abstractio...Neural networks are hypothesized to implement interpretable causal mechanisms, yet verifying this requires finding a causal abstraction -- a simpler, hi...113Efficient Targeted Maximum Likelihood Estimators for...In a typical two-phase design, a random sample is drawn from the target population in phase 1, during which only a subset of variables is collected. In...114Enhancing Spatial Understanding in Image Generation...Recent progress in text-to-image generation has greatly advanced visual fidelity and creativity, but it has also imposed higher demands on prompt comple...115Fairness under Graph Uncertainty: Achieving Interven...Algorithmic decisions about individuals require predictions that are not only accurate but also fair with respect to sensitive attributes such as gender...116FaultXformer: A Transformer-Encoder Based Fault Clas...Accurate fault detection and localization in electrical distribution systems is crucial, especially with the increasing integration of distributed energ...117Fixed Anchors Are Not Enough: Dynamic Retrieval and...Decoupled dataset distillation (DD) compresses large corpora into a few synthetic images by matching a frozen teacher's statistics. However, current res...118General Bayesian Policy LearningThis study proposes the General Bayes framework for policy learning. We consider decision problems in which a decision-maker chooses an action from an a...119GeoDiff4D: Geometry-Aware Diffusion for 4D Head Avat...Reconstructing photorealistic and animatable 4D head avatars from a single portrait image remains a fundamental challenge in computer vision. While diff...120Hierarchical Action Learning for Weakly-Supervised A...Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features,...121Histopathology Image Normalization via Latent Manifo...Batch effects arising from technical variations in histopathology staining protocols, scanners, and acquisition pipelines pose a persistent challenge fo...122HumanOrbit: 3D Human Reconstruction as 360° Orbit Ge...We present a method for generating a full 360° orbit video around a person from a single input image. Existing methods typically adapt image-based diffu...123Hypothesis Testing over Observable Regimes in Singul...Hypothesis testing in singular statistical models is often regarded as inherently problematic due to non-identifiability and degeneracy of the Fisher in...124Joint Geometric and Trajectory Consistency Learning...Diffusion-based Real-World Image Super-Resolution (Real-ISR) achieves impressive perceptual quality but suffers from high computational costs due to ite...125Learning Flexible Job Shop Scheduling under Limited...The Flexible Job Shop Scheduling Problem (FJSP) originates from real production lines, while some practical constraints are often ignored or idealized i...126LemmaBench: A Live, Research-Level Benchmark to Eval...We present a new approach for benchmarking Large Language Model (LLM) capabilities on research-level mathematics. Existing benchmarks largely rely on st...127Manifold-Preserving Superpixel Hierarchies and Embed...High-dimensional images, or images with a high-dimensional attribute vector per pixel, are commonly explored with coordinated views of a low-dimensional...128Memory Caching: RNNs with Growing MemoryTransformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity...129Mode Seeking meets Mean Seeking for Fast Long Video...Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form d...130Moment Matters: Mean and Variance Causal Graph Disco...Heteroscedasticity -- where the variance of a variable changes with other variables -- is pervasive in real data, and elucidating why it arises from the...131MT-PingEval: Evaluating Multi-Turn Collaboration wit...We present a scalable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective...132Multimodal Optimal Transport for Unsupervised Tempor...Recognizing surgical phases and steps from video is a fundamental problem in computer-assisted interventions. Recent approaches increasingly rely on lar...133Multivariate Spatio-Temporal Neural Hawkes ProcessesWe propose a Multivariate Spatio-Temporal Neural Hawkes Process for modeling complex multivariate event data with spatio-temporal dynamics. The proposed...134MuViT: Multi-Resolution Vision Transformers for Lear...Modern microscopy routinely produces gigapixel images that contain structures across multiple spatial scales, from fine cellular morphology to broader t...135Neural Diffusion Intensity Models for Point Process...Cox processes model overdispersed point process data via a latent stochastic intensity, but both nonparametric estimation of the intensity model and pos...136Preference Packing: Efficient Preference Optimizatio...Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. I...137Prune Wisely, Reconstruct Sharply: Compact 3D Gaussi...Recent significant advances in 3D scene representation have been driven by 3D Gaussian Splatting (3DGS), which has enabled real-time rendering with phot...138RAViT: Resolution-Adaptive Vision TransformerVision transformers have recently made a breakthrough in computer vision showing excellent performance in terms of precision for numerous applications....139Recycling Failures: Salvaging Exploration in RLVR vi...Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the complex reasoning capabilities of Large Reaso...140Resilient Strategies for Stochastic Systems: How Muc...We study the problem of resilient strategies in the presence of uncertainty. Resilient strategies enable an agent to make decisions that are robust agai...141Resources for Automated Evaluation of Assistive RAG...Many readers today struggle to assess the trustworthiness of online news because reliable reporting coexists with misinformation. The TREC 2025 DRAGUN (...142RewardUQ: A Unified Framework for Uncertainty-Aware...Reward models are central to aligning large language models (LLMs) with human preferences. Yet most approaches rely on pointwise reward estimates that o...143SafeGen-LLM: Enhancing Safety Generalization in Task...Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based...144SenCache: Accelerating Diffusion Model Inference via...Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoisin...145SongSong: A Time Phonograph for Chinese SongCi Music...Recently, there have been significant advancements in music generation. However, existing models primarily focus on creating modern pop songs, making it...146Taming Momentum: Rethinking Optimizer States Through...Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces sig...147Task Complexity Matters: An Empirical Study of Reaso...Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across langu...148Task-Centric Acceleration of Small-Language ModelsSmall language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often emp...149Terminology Rarity Predicts Catastrophic Failure in...This study presents the first systematic, reference-free human evaluation of large language model (LLM) machine translation (MT) for Ancient Greek (AG)...150The Stability of Online Algorithms in Performative P...The use of algorithmic predictions in decision-making leads to a feedback loop where the models we deploy actively influence the data distributions we s...151Time Series Foundation Models as Strong Baselines in...Accurate forecasting of transportation dynamics is essential for urban mobility and infrastructure planning. Although recent work has achieved strong pe...152Toward Guarantees for Clinical Reasoning in Vision L...Vision-language models (VLMs) show promise in drafting radiology reports, yet they frequently suffer from logical inconsistencies, generating diagnostic...153UFO-4D: Unposed Feedforward 4D Reconstruction from T...Dense 4D reconstruction from unposed images remains a critical challenge, with current methods relying on slow test-time optimization or fragmented, tas...154Uncertainty Quantification for Multimodal Large Lang...Despite their capabilities, Multimodal Large Language Models (MLLMs) may produce plausible but erroneous outputs, hindering reliable deployment. Accurat...155VaSST: Variational Inference for Symbolic Regression...Symbolic regression has recently gained traction in AI-driven scientific discovery, aiming to recover explicit closed-form expressions from data that re...156Who Guards the Guardians? The Challenges of Evaluati...Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with known ground-...
