Yang Liu

32 papers CUHK

• Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
• Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
• CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design
• Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
• DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization
• DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding
• DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
• Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
• Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
• Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth
• Exploring Structural Degradation in Dense Representations for Self-supervised Learning
• Federated Continual Learning via Orchestrating Multi-Scale Expertise
• Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations
• INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
• Incentivizing LLMs to Self-Verify Their Answers
• LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
• LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
• Latent Retrieval Augmented Generation of Cross-Domain Protein Binders
• Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields
• Learning CAD Modeling Sequences via Projection and Part Awareness
• Learning Counterfactual Outcomes Under Rank Preservation
• MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
• MOF-BFN: Metal-Organic Frameworks Structure Prediction via Bayesian Flow Networks
• Mesh Interpolation Graph Network for Dynamic and Spatially Irregular Global Weather Forecasting
• Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation
• PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
• Quadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuning
• Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection
• SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
• SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
• TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer
• Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration