Zeliang Zhang

zeliang0426's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 17 days ago

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

Paper • 2510.01586 • Published Oct 2 • 1

Directional Reasoning Injection for Fine-Tuning MLLMs

Paper • 2510.15050 • Published Oct 16 • 11

authored 9 papers about 2 months ago

One Forward is Enough for Neural Network Training via Likelihood Ratio Method

Paper • 2305.08960 • Published May 15, 2023

Video Understanding with Large Language Models: A Survey

Paper • 2312.17432 • Published Dec 29, 2023 • 3

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?

Paper • 2411.10979 • Published Nov 17, 2024

Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See

Paper • 2410.06169 • Published Oct 8, 2024

Generative AI for Cel-Animation: A Survey

Paper • 2501.06250 • Published Jan 8 • 13

From 16-Bit to 1-Bit: Visual KV Cache Quantization for Memory-Efficient Multimodal Large Language Models

Paper • 2502.14882 • Published Feb 15

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

Paper • 2504.05541 • Published Apr 7 • 15

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness

Paper • 2505.20426 • Published May 26 • 7

Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models

Paper • 2510.05034 • Published Oct 6 • 48