35 papers
An Executable Benchmarking Suite for Tool-Using Agents
Zhiqing Zhong, Zhijing Ye, Jiamin Wang +1
Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating dri…
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving
Zhiqing Zhong, Zhijing Ye, Jian Zhang +3
Static-graph LLM decoders provide predictable launches, fixed tensor shapes, and low submission overhead, but online decoding exposes highly irregular KV-cache behavior: request le…
TLRD: Teaching LLMs to Reason over Tabular Data with Tri-Level Rationale Distillation
Tianyuan Liang, Xuwei Tan, Lei Shi +6
Tabular data is a primary medium for storing real-world information, driving many industrial applications of machine learning. Traditional predictors achieve strong predictive perf…
Residual Skill Optimization for Text-to-SQL Ensembles
Jiongli Zhu, Haoquan Guan, Parjanya Prajakta Prashant +8
Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability t…
NCCLZ: Compression-Enabled GPU Collectives with Decoupled Quantization and Entropy Coding
Jiamin Wang, Zhijing Ye, Xiaodong Yu
Collective communication is a major bottleneck for multi-node GPU workloads in scientific computing and distributed deep learning, especially when inter-node bandwidth is limited.…
DRIFT: Transferring Reasoning Priors for Efficient MLLM Fine-Tuning
Chao Huang, Zeliang Zhang, Jiang Liu +7
Multimodal large language models (MLLMs) have made rapid progress, yet their reasoning ability often lags behind strong text-only LLMs. Bridging this gap typically requires large-s…