activity
20242026
collaborators

11 papers

cs.AI2026

DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail

He Liu, Changtao Miao, Xinjie Yang +12

Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation. E…

cs.LG2026

RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference

Wenhao Li, Jinhao Dong, Hailin Zhang +3

Long-context Large Language Model inference is severely bottlenecked by the massive Key-Value (KV) cache, yet existing sparse attention methods often suffer from static fixed-budge…

cs.CL2026

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Ang Li, Ben Liu, Bin Han +215

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve,…

cs.AI2026

Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

Long P. Hoang, Hai V. Le, Shaoyang Xu +2

Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In…

cs.AI2026

Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

Long P. Hoang, Yiran Zhao, Wei Lu +1

The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tuning these models frequently…

cs.CL2026

DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation

Yuyang Gong, Miaokun Chen, Jiawei Liu +5

Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retri…