11 papers
Self-Evolving Defense: Continual Security Policy Learning for LLM Agents
Minh Nhat Le, Nisarga Gondi, Yibo Peng +4
Large language models (LLMs) increasingly power agents that access sensitive information, use external tools, and modify software repositories. Although these capabilities offer su…
Reliable and Responsible Foundation Models: A Comprehensive Survey
Xinyu Yang, Junlin Han, Rishi Bommasani +49
Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), a…
ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System
Hao Kang, Ziyang Li, Weili Xu +7
Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inf…
MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution
Jianwen Chen, Xinyu Yang, Peng Xia +7
Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequential autoregressive decoding f…
When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
Yibo Peng, James Song, Lei Li +6
Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively on functional correctness. In th…
RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
Yongji Wu, Xueshen Liu, Haizhong Zheng +5
Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows involve interleaving rollout and traini…
Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
Xinyu Yang, Yuwei An, Hongyi Liu +2
Autoregressive Large Language Models (AR-LLMs) frequently exhibit implicit parallelism in sequential generation. Inspired by this, we introduce Multiverse, a new generative model t…
APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
Xinyu Yang, Tianqi Chen, Beidi Chen
Context-augmented generation (CAG) techniques, including RAG and ICL, require the efficient combination of multiple contexts to generate responses to user queries. Directly inputti…
SFT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
Xinyu Yang, Jixuan Leng, Geyang Guo +5
Current PEFT methods for LLMs can achieve either high quality, efficient training, or scalable serving, but not all three simultaneously. To address this limitation, we investigate…
VcLLM: Video Codecs are Secretly Tensor Codecs
Ceyu Xu, Yongji Wu, Xinyu Yang +4
As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottleneck…
It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF
Taiming Lu, Lingfeng Shen, Xinyu Yang +3
Reinforcement Learning from Human Feedback (RLHF) involves training policy models (PMs) and reward models (RMs) to align language models with human preferences. Instead of focusing…