Yuzhang Shang

Real-Time Robot Execution with Masked Action Chunking

Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization

Distilling Video Datasets into Images

TemporalBench: Evaluating Fine-Grained Temporal Dynamics Understanding for Multimodal Models

ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms

ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows

Efficient Multimodal Dataset Distillation via Generative Models

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Prompt Diffusion Robustifies Any-Modality Prompt Learning

TemporalBench: Towards Fine-grained Temporal Understanding for Multimodal Video Models

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models