AI.info
Yang Liu
Explore Yang Liu on AI.info.
- Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
- O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
- KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
- OccTrack360: 4D Panoptic Occupancy Tracking from Surround-View Fisheye Cameras
- MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing
- Unified Biomolecular Trajectory Generation via Pretrained Variational Bridge
- From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
- Live or Lie: Action-Aware Capsule Multiple Instance Learning for Risk Assessment in Live Streaming Platforms
- CloDS: Visual-Only Unsupervised Cloth Dynamics Learning in Unknown Conditions
- Skywork UniPic 3.0: Unified Multi-Image Composition via Sequence Modeling
- Resisting Manipulative Bots in Meme Coin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning
- BabyVision: Visual Reasoning Beyond Language
- Spatial4D-Bench: A Versatile 4D Spatial Intelligence Benchmark
- Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
- HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
- Measuring the Unspoken: A Disentanglement Model and Benchmark for Psychological Analysis in the Wild
- Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
- Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
- VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning
- Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering
- I2E: Real-Time Image-to-Event Conversion for High-Performance Spiking Neural Networks
- DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
- G2: Guided Generation for Enhanced Output Diversity in LLMs
- MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
- Uniform Discrete Diffusion with Metric Path for Video Generation
- JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence
- VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series
- Weight Decay may matter more than muP for Learning Rate Transfer in Practice
- Exploring Structural Degradation in Dense Representations for Self-supervised Learning
- Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
- PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
- SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG