AI研究论文每日精选

Mutarjim: Advancing Bidirectional Arabic-English Translation with a Small Language Model

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Alchemist: Turning Public Text-to-Image Data into Generative Gold

BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs

PATS: Process-Level Adaptive Thinking Mode Switching

Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance

ARM: Adaptive Reasoning Model

Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

B-score: Detecting biases in large language models using response history

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers

Lifelong Safety Alignment for Language Models

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps

Flex-Judge: Think Once, Judge Anywhere

Learning to Reason without External Rewards

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models

StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs

Discrete Markov Bridge

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning

Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition

ModernGBERT: German-only 1B Encoder Model Trained from Scratch

AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation

Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning

Interleaved Reasoning for Large Language Models via Reinforcement Learning

Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI

Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals

From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference

WHISTRESS: Enriching Transcriptions with Sentence Stress Detection

Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time

The Coverage Principle: A Framework for Understanding Compositional Generalization

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models

STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs

InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction

Accelerating Nash Learning from Human Feedback via Mirror Prox

Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models

Jodi: Unification of Visual Generation and Understanding via Joint Modeling

Dynamic Risk Assessments for Offensive Cybersecurity Agents

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scenes

DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue

An Embarrassingly Simple Defense Against LLM Abliteration Attacks

Hybrid Latent Reasoning via Reinforcement Learning

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation

UFT: Unifying Supervised and Reinforcement Fine-Tuning

EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision

TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification

Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey

DiSA: Diffusion Step Annealing in Autoregressive Image Generation

EgoZero: Robot Learning from Smart Glasses

Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models

FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models

MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs

The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models

The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models

InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning

CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning