Wanli Ouyang

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery

Interleaving Reasoning for Better Text-to-Image Generation

CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

High Performance Space Debris Tracking in Complex Skylight Backgrounds with a Large-Scale Dataset

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

UniMind: Unleashing the Power of LLMs for Unified Multi-Task Brain Decoding

Chem-R: Learning to Reason as a Chemist

PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level

ChemBOMAS: Accelerated Bayesian Optimization for Scientific Discovery in Chemistry with LLM-Enhanced Multi-Agent System

AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use

GLARE: Towards Graph-less Retrieval for Retrieval Augmented Generation on Million-scale Knowledge Graphs

LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?

Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models

PhysicsMinions: Winning Gold Medals in the Latest Physics Olympiads with a Coevolutionary Multimodal Multi-Agent System

CompBench: Benchmarking Complex Instruction-guided Image Editing

A Unified Perspective and Review on Tree Search for LLMs Test-Time Scaling

TinyEye: Sharpening Visual Reasoning of Tiny Models with Offline Policy Optimization

Knowledge-to-Verification: Unlocking Reinforcement Learning with Verifiable Rewards for LLMs in Knowledge-Intensive Domains

Enabling Thinking, Reflecting and Chain-of-Thought Reasoning with Biological Sequences

Rethinking Multi-Omics LLMs from the Perspective of Omics-Encoding

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Why Do LLMs Fail at Arithmetic Logic? A Diagnosis of Limits on Sequential Computation

Nature-Inspired Population-Based Evolution of Large Language Models

CTTS: Collective Test-Time Scaling

EWE: An Agentic Framework for Extreme Weather Analysis

Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback

Test-Time Layer Recurrence Enables Ultra-Deep Thinking in LLMs Without Chain-of-Thought

Finetuning Large Language Model as an Effective Symbolic Regressor

Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models

SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning

A CLIP-Powered Framework for Robust and Generalizable Data Selection

Flow-GRPO: Training Flow Matching Models via Online RL

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

FuncGenFoil: Airfoil Generation and Editing Model in Function Space

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration

Native-Resolution Image Synthesis

Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation

Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization

CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models

Depth Any Video with Scalable Synthetic Data

Neural Representational Consistency Emerges from Probabilistic Neural-Behavioral Representation Alignment

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

Improving Video Generation with Human Feedback

Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction

WorldSimBench: Towards Video Generation Models as World Simulators

COMET: Benchmark for Comprehensive Biological Multi-omics Evaluation Tasks and Language Models

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

PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling

VEnhancer: Generative Space-Time Enhancement for Video Generation

MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data

MindDETR: Beyond Semantics, Exploring Positional Cues from Brain Activity

Biology Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models

Diffusion Models Need Visual Priors for Image Generation

OASIS: Open Agents Social Interaction Simulations on a Large Scale

Transforming Ocean Analysis: Learning 4D ocean field from in-situ observations via uncertainty-aware implicit representations

Two Heads Are Better Than One: A Multi-Agent System Has the Potential to Improve Scientific Idea Generation

SimDiffPDE: Simple Diffusion Baselines for Solving Partial Differential Equations