Large Language Models

FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models

Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models

Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language Modeling

Reanalyzing L2 Preposition Learning with Bayesian Mixed Effects and a Pretrained Language Model

Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures

LLM Reasoning with Process Rewards for Outcome-Guided Steps

Haiku to Opus in Just 10 bits: LLMs Unlock Massive Compression Gains

DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery

OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration

An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code

Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning

Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis

Internalized Reasoning for Long-Context Visual Document Understanding

Variational Encoder--Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition

Improving MPI Error Detection and Repair with Large Language Models and Bug References

Do We Need Frontier Models to Verify Mathematical Proofs?

Skeleton-based Coherence Modeling in Narratives

When simulations look right but causal effects go wrong: Large language models as behavioral simulators

On the Geometric Structure of Layer Updates in Deep Language Models

Hierarchical, Interpretable, Label-Free Concept Bottleneck Model

Generating Satellite Imagery Data for Wildfire Detection through Mask-Conditioned Generative AI

Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Models

Token-Efficient Multimodal Reasoning via Image Prompt Packaging

An Explainable Vision-Language Model Framework with Adaptive PID-Tversky Loss for Lumbar Spinal Stenosis Diagnosis

Social Meaning in Large Language Models: Structure, Magnitude, and Pragmatic Prompting

Opal: Private Memory for Personal AI

Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits

From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks

Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation

Understanding the Effects of Safety Unalignment on Large Language Models

High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination

Moondream Segmentation: From Words to Masks

Making Written Theorems Explorable by Grounding Them in Formal Representations

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Analytic Drift Resister for Non-Exemplar Continual Graph Learning

Speaking of Language: Reflections on Metalanguage Research in NLP

GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers

Generalization Limits of Reinforcement Learning Alignment

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

Too Polite to Disagree: Understanding Sycophancy Propagation in Multi-Agent Systems

Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems

Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis

Finding Belief Geometries with Sparse Autoencoders

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs

Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints

Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy

V2X-QA: A Comprehensive Reasoning Dataset and Benchmark for Multimodal Large Language Models in Autonomous Driving Across Ego, Infrastructure, and Cooperative Views