Yang Liu

Kimi-Dev: Agentless Training as Skill Prior for SWE-agents

DrugTrail: Interpretable Drug Discovery via Structured Reasoning and Druggability‑Tailored Preference Optimization

Unified Biomolecular Trajectory Generation via Pretrained Variational Bridge

Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning

Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning

AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection

GraphPlan: Graph-enhanced Planning via Thinking LLMs for Embodied Agents

Agent-Environment Alignment via Automated Interface Generation

Visual Abstract Thinking: Enhancing Multimodal Reasoning via Visual Abstraction

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agent's Inquiry Capability

Transparent and Robust RAG: Adaptive-Reward Reinforcement Learning for Decision Traceability

Inference-Time Scaling for Generalist Reward Modeling

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks

Benchmarking Long-Term Memory with Continuous dialogue Lifelogs

HBDrug3D: A Dataset and Benchmark for AI-Driven Heterobifunctional Molecule Design

UR$^2$: Unify RAG and Reasoning through Reinforcement Learning

SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts

MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow Networks

Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields

Force-Guided Bridge Matching for Full-Atom Time-Coarsened Dynamics of Peptides

UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design

Latent Retrieval Augmented Generation of Cross-Domain Protein Binders

Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations

FormaRL: Enhancing Autoformalization with no Labeled Data

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

UniSim: A Unified Simulator for Time-Coarsened Dynamics of Biomolecules

Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization

Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints

VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI

ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models

Enabling Weak LLMs to Judge Response Reliability via Meta Ranking

Enhancing Multi-Agent Learning in Real-World Interactive Environments through Process Reward Decomposition