Xiangyang Ji

Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learning

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models

EventFlash: Towards Efficient MLLMs for Event-Based Vision

Enhancing Reasoning in Large Language Models via Entropy-Aware Self-Evolution

Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection

MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language Generalization

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution

HINT: Hierarchical Interaction Modeling for Autoregressive Multi-Human Motion Generation

A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth

FlattenGPT: Depth Compression for Transformer with Layer Flattening

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

Adaptive Nonlinear Compression for Large Foundation Models

DiHiRA: Diagonal High-Rank Adaption for Large Foundation Models

A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments

Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy

Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits

Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection

Variation-Bounded Losses for Learning with Noisy Labels

Are High-Quality AI-Generated Images More Difficult for Models to Detect?

Adaptive HL-Gaussian: A Value Function Learning Method with Dynamic Support Adjustment

Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration

Rethinking Brain-to-Image Reconstruction: What Should We Decode from fMRI Signals?

Communication-Efficient Federated Learning via Model Update Distillation