109 citations · 179 across the 12 of their papers we have counts for
13 papers
HoloAegis: Frozen Representation, Topological Inference --- Minimally Parametric Safety Manifolds and Their Capability Boundaries for LLM Guardrails
Tak Ho Alex Li, Kaijie Liu, Lik-Hang Lee +3
Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representations while generative judges incur prohibitive inference costs. We ask a compl…
DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
Jinyu Guo, Zhihan Zhang, Jiehui Xie +7
The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing…
From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
Yitian Zhou, Chaoning Zhang, Jiaquan Zhang +6
Long-context large language models remain computationally expensive to run and often fail to reliably process very long inputs, which makes context compression an important compone…
Experience Transfer for Multimodal LLM Agents in Minecraft Game
Chenghao Li, Jun Liu, Songbo Zhang +7
Multimodal LLM agents operating in complex game environments must continually reuse past experience to solve new tasks efficiently. In this work, we propose Echo, a transfer-orient…
Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain
Jiaquan Zhang, Chaoning Zhang, Shuxu Chen +9
Chain-of-Thought (CoT) has been shown to significantly improve the reasoning accuracy of large language models (LLMs) on complex tasks. However, due to the autoregressive, step-by-…
LMLPA: Language Model Linguistic Personality Assessment
Jingyao Zheng, Xian Wang, Simo Hosio +2
Large Language Models (LLMs) are increasingly used in everyday life and research. One of the most common use cases is conversational interactions, enabled by the language generatio…
DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling
Haoran Li, Haolin Shi, Wenli Zhang +5
Text-to-3D scene generation holds immense potential for the gaming, film, and architecture sectors. Despite significant progress, existing methods struggle with maintaining high qu…
Sora as a World Model? A Complete Survey on Text-to-Video Generation
Fachrina Dewi Puspitasari, Chaoning Zhang, Joseph Cho +13
The evolution of video generation from text, from animating MNIST to simulating the world with Sora, has progressed at a breakneck speed. Here, we systematically discuss how far te…
A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering
Chaoning Zhang, Joseph Cho, Fachrina Dewi Puspitasari +11
The Segment Anything Model (SAM), developed by Meta AI Research, represents a significant breakthrough in computer vision, offering a robust framework for image and video segmentat…
Last Week with ChatGPT: A Weibo Study on Social Perspective Regarding ChatGPT for Education and Beyond
Yao Tian, Chengwei Tong, Lik-Hang Lee +3
The application of AI-powered tools has piqued the interest of many fields, particularly in the academic community. This study uses ChatGPT, currently the most powerful and popular…
Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era
Chenghao Li, Chaoning Zhang, Joseph Cho +6
Generative AI has made significant progress in recent years, with text-guided content generation being the most practical as it facilitates interaction between human instructions a…
What if we have Meta GPT? From Content Singularity to Human-Metaverse Interaction in AIGC Era
Lik-Hang Lee, Pengyuan Zhou, Chaoning Zhang +1
The global metaverse development is facing a "cooldown moment", while the academia and industry attention moves drastically from the Metaverse to AI Generated Content (AIGC) in 202…
A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?
Chaoning Zhang, Chenshuang Zhang, Sheng Zheng +14
As ChatGPT goes viral, generative AI (AIGC, a.k.a AI-generated content) has made headlines everywhere because of its ability to analyze and create text, images, and beyond. With su…