Papers

HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation

Demonstration of Space Robot Teleoperation over a Lossy and Delayed Network using ATMOS

CAKE: Compiler–Agent Co-Design for Frontier Kernel Evolution

Training AI Scientists to Replicate Research

Small-Scale Experiments: Are We There Yet?

How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review

Intern-S2-Preview: Scientific Agentic Foundation Model

DarwinX: Evolving Agent Harnesses Through Natural Selection

DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation

Alaya-EVOKE: From Linear-Scaling Supervision to Endless World

LLMROUTER: UNIFIED INFRASTRUCTURE FOR DEVELOPING, EVALUATING, AND DEPLOYING LLM ROUTERS

ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents

Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models

StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

WizardLM: EMPOWERING LARGE PRE-TRAINED LANGUAGE MODELS TO FOLLOW COMPLEX INSTRUCTIONS

Indoor Segmentation and Support Inference from RGBD Images

Evaluating Language Models for Harmful Manipulation

SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

MENDEL GÖDEL MACHINE: RECURSIVE SELF-IMPROVING CODING AGENTS VIA COMPARATIVE EVOLUTION

Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence