Liang Wang

AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

Variational Reasoning for Language Models

Thyme: Think Beyond Images

PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization

BaseReward: A Strong Baseline for Multimodal Reward Model

MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models

ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models

VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks

OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing

UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models

C$^3$-Bench: Evaluating and Achieving Controllable Code Completion in Code LLM

Real-Time Evaluation for Novel Class Discovery at Test Time

Reinforcing General Reasoning Without Verifiers

Conformal Uncertainty Indicator for Continual Test-Time Adaptation

From Genomic Whispers to Therapeutics: Multi-Resolution Transcriptome-Guided Diffusion Models for Drug Design and Screening

Binding Mode Matters: Residue-Guided Drug Discovery via Explorative Preferences

Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation

BridgeV2W: Bridging Video Generation Models to Embodied World Models via Embodiment Masks

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

EgoDemoGen: Novel Egocentric Demonstration Generation Enables Viewpoint-Robust Manipulation

DAA: Amplifying Unknown Discrepancy for Test-Time Discovery

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection

MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra

Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Graffe: Graph Representation Learning Enabled via Diffusion Probabilistic Models

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Hierarchical Multimodal Knowledge Matching for Training-Free Open-Vocabulary Object Detection

TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting

CONSTRAINT-AWARE ZERO-SHOT VISION-LANGUAGE NAVIGATION IN CONTINUOUS ENVIRONMENTS

Dual Flows with Contrastive Guidance for Generating Highly Designable Proteins

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining

TUI: A Conformal Uncertainty Indicator for Continual Test-Time Adaptation

Controllable Continual Test-Time Adaptation