activity
20242026
most citedWhere LLM Agents Fail and How They can Learn From Failures

3 citations · 3 across the 16 of their papers we have counts for

collaborators

24 papers

cs.CL2026

Reliable Use of Lemmas via Eligibility Reasoning and SectionAware Reinforcement Learning

Zhikun Xu, Xiaodong Yu, Ben Zhou +6

Recent large language models (LLMs) perform strongly on mathematical benchmarks yet often misapply lemmas, importing conclusions without validating assumptions. We formalize lemma$…

cs.CL2026

CD4LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models

Yihao Liang, Ze Wang, Hao Chen +7

Autoregressive large language models achieve strong results on many benchmarks, but decoding remains fundamentally latency-limited by sequential dependence on previously generated…

cs.AR2025

DABench-LLM: Standardized and In-Depth Benchmarking of Post-Moore Dataflow AI Accelerators for LLMs

Ziyu Hu, Zhiqing Zhong, Weijian Zheng +6

The exponential growth of large language models has outpaced the capabilities of traditional CPU and GPU architectures due to the slowdown of Moore's Law. Dataflow AI accelerators…

cs.CL2025

Instella: Fully Open Language Models with Stellar Performance

Jiang Liu, Jialian Wu, Xiaodong Yu +10

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, yet the majority of high-performing models remain closed-source or partially ope…

cs.LG2025

An Efficient Gradient-Aware Error-Bounded Lossy Compressor for Federated Learning

Zhijing Ye, Sheng Di, Jiamin Wang +3

Federated learning (FL) enables collaborative model training without exposing clients' private data, but its deployment is often constrained by the communication cost of transmitti…

cs.CV2025

Learning from Online Videos at Inference Time for Computer-Use Agents

Yujian Liu, Ze Wang, Hao Chen +7

Computer-use agents can operate computers and automate laborious tasks, but despite recent rapid progress, they still lag behind human users, especially when tasks require domain-s…