Tat-Seng Chua

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking

JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization

PerFit: Exploring Personalization Shifts in Representation Space of LLMs

NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching

Discrete Diffusion for Bundle Construction

RoboOmni: Proactive Robot Manipulation in Omni-modal Context

TTOM: Test-Time Optimization and Memorization for Compositional Video Generation

JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation

NextQuill: Causal Preference Modeling for Enhancing LLM Personalization

VINCIE: Unlocking In-context Image Editing from Video

Reinforced Latent Reasoning for LLM-based Recommendation

Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation

A Reason-then-Describe Instruction Interpreter for Controllable Video Generation

Reasoning on Time-Series for Financial Technical Analysis

Interpreting Any Condition to Caption for Controllable Video Generation

AUHead: Realistic Emotional Talking Head Generation via Action Units Control

Equipping LLMs with Self-Awareness for High-Stakes Tasks

RLPR: Extrapolating RLVR to General Domains without Verifiers

Quicksviewer: An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

AnyEdit: Edit Any Knowledge Encoded in Language Models

On Path to Multimodal Generalist: General-Level and General-Bench

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models

FOCoOp: Enhancing Out-of-Distribution Robustness in Federated Prompt Learning for Vision-Language Models

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Language Representations Can be What Recommenders Need: Findings and Potentials

Continual Multimodal Contrastive Learning

IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation

Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

On Reasoning Strength Planning in Large Reasoning Models

VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation

Efficient Inference for Large Language Model-based Generative Recommendation

DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization

Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation

TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models

Counterfactual Evolution of Multimodal Datasets via Visual Programming

The Emergence of Abstract Thought in Large Language Models Beyond Any Language

Neural Causal Graph for Interpretable and Intervenable Classification

Towards Semantic Equivalence of Tokenization in Multimodal LLM

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

Preference Diffusion for Recommendation

Long-Term TalkingFace Generation via Motion-Prior Conditional Diffusion Model

Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark

NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation

Towards Comprehensive and Efficient Post Safety Alignment of Large Language Models via Safety Patching

Progressive Multi-scale Triplane Network for Text-to-3D Generation

Unified Music-Language Model for Symbolic and Waveform Integration

Massively Multi-Agents Reveal That Large Language Models Can Understand Value

MMDocBench: Benchmarking Large Vision-Language Models for Fine-Grained Visual Document Understanding

Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector