Dongzhan Zhou

AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception

SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward

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

Speak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation

Δ-AttnMask: Attention-Guided Masked Hidden States for Efficient Data Selection and Augmentation

SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy

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

DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Data Selection

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

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

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning

HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?

AtomWorld: Benchmarking Spatial Reasoning in Large Language Models on Crystalline Materials

MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models

Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback

Object-AVEdit: An Object-level Audio-Visual Editing Model

SmartMat Explorer: Automated scientific research for materials discovery

Accelerating 3D Molecule Generative Models with Trajectory Diagnosis

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?

MokA: Multimodal Low-Rank Adaptation for MLLMs

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward

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

A CLIP-Powered Framework for Robust and Generalizable Data Selection

When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration

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

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

MolReFlect: Towards Fine-grained In-Context Alignment between Molecules and Texts

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