ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents

Your Group-Relative Advantage Is Biased

STEM: Scaling Transformers with Embedding Modules

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning

VIBE: Visual Instruction Based Editor

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

STEP3-VL-10B Technical Report

SeedFold: Scaling Biomolecular Structure Prediction

TranslateGemma Technical Report

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL

A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation

Controlled Self-Evolution for Algorithmic Code Optimization

MAXS: Meta-Adaptive Exploration with LLM Agents

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

The motivic class of the space of genus 0 maps to the flag variety

UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training

EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs

Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization

How Do Large Language Models Learn Concepts During Continual Pre-Training?

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents

Your Group-Relative Advantage Is Biased

STEM: Scaling Transformers with Embedding Modules

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning

VIBE: Visual Instruction Based Editor

Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Urban Socio-Semantic Segmentation with Vision-Language Reasoning

STEP3-VL-10B Technical Report

SeedFold: Scaling Biomolecular Structure Prediction

TranslateGemma Technical Report

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis via Dynamic Visual Encoding and Staged RL

A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation

Controlled Self-Evolution for Algorithmic Code Optimization

MAXS: Meta-Adaptive Exploration with LLM Agents

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

The motivic class of the space of genus 0 maps to the flag variety

UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training

EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs

Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization

How Do Large Language Models Learn Concepts During Continual Pre-Training?

JudgeRLVR: Judge First, Generate Second for Efficient Reasoning

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices