activity
20232026
most citedTowards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

17 citations · 53 across the 33 of their papers we have counts for

collaborators
Showing cs.CLShow all

19 papers · 1 filter

cs.CL2026

Practical Online KV Cache Compaction for LLM Agents: An Empirical Study

Yujian Liu, Jiabao Ji, Li An +4

LLM agents accumulate long trajectories of reasoning steps, tool calls, and environment feedback, making the KV cache a major inference bottleneck. KV cache compaction can reduce t…

cs.CL2026

Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning

Congrui Du, Yang Zhang, Kaizhi Qian +1

Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires learning a new modality and…

cs.CL2026

VISUALSKILL: Multimodal Skills for Computer-Use Agents

Ziyan Jiang, Li An, Yujian Liu +5

Computer-use agents (CUAs) approach human-level performance on standardised benchmarks but still struggle on long-horizon tasks and unseen software. Existing skill libraries addres…

cs.CL2026★ 4 cited

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

Yujian Liu, Jiabao Ji, Li An +3

Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage perform…

cs.CL2025

DEEPAMBIGQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness

Jiabao Ji, Min Li, Priyanshu Kumar +2

Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle to produce complete answer set to comp…

cs.CL2025

ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Bairu Hou, Yang Zhang, Jiabao Ji +4

We present ThinkPrune, a simple yet effective method for pruning the thinking length for long-thinking LLMs, which has been found to often produce inefficient and redundant thinkin…