8 papers
Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Yuxuan Wang, Guangxiang Zhao, Xinyu Tan +6
Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps those probabilities and also pe…
ArborMem: Navigating Interaction States with Memory Forests
Zongwei Lv, Yuemeng Xu, Yilun Yao +8
Large language models increasingly serve as persistent conversational assistants, requiring memory that preserves relevant experience and maintains continuity across interactions.…
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
Zongwei Lv, Yaoming Li, Zhewen Tan +7
Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introd…
Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
Yilun Yao, Xinyu Tan, Chao-Hsuan Liu +10
LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the…
Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
Weihong Lin, Lin Sun, Qilong Shi +6
Model merging has emerged as a promising paradigm for composing the capabilities of large language models by directly operating in weight space, enabling the integration of special…
KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
Aomufei Yuan, Zhiming Wang, Ruijie Miao +8
As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batc…
KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
Yuxuan Tian, Zihan Wang, Yebo Peng +6
Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional meth…
FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference
Bingzhe Zhao, Ke Cheng, Aomufei Yuan +5
KV cache techniques in Transformer models aim to reduce redundant computations at the expense of substantially increased memory usage, making KV cache compression an important and…