activity
20242026
collaborators

26 papers

cs.LG2026

SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding

Jiamu Zhang, Liang Wu, Kelly Wan +2

Large language models (LLMs) increasingly read long inputs in the agentic era, from whole documents and codebases to conversations across many turns. Their inference memory is then…

cs.CV2026

Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering

Haotian Xia, Zilin Xiao, Junbo Zou +2

Video question answering requires models to ground language queries in visual evidence and, when necessary, reason over that evidence across time. Existing methods typically rely o…

cs.CR2026

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems

Lingxi Zhang, Guangtao Zheng, Hanjie Chen

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this commun…

cs.CL2026

Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning

Zilin Xiao, Qi Ma, Chun-cheng Jason Chen +4

Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic si…

cs.CY2026

Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions

Saleh Afroogh, Syed Ishtiaque Ahmed, Petra Ahrweiler +46

This study provides a cross-disciplinary examination of Explainable Artificial Intelligence (XAI) approaches-focusing on deep neural networks (DNNs) and large language models (LLMs…

cs.LG2026

LT2: Linear-Time Looped Transformers

Chunyuan Deng, Yizhe Zhang, Rui-Jie Zhu +4

Looped Transformers (LT) have emerged as a powerful architecture by iterating their layers multiple times before decoding the final token. However, pairing them with full attention…