28 papers
PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents
Zhi-Kai Chen, Xu-Xiang Zhong, Song-Yan Li +2
LLM agents increasingly solve tasks by invoking multiple tools, where parallel execution is essential for low latency but difficult to manage safely. Existing agent benchmarks prim…
ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping
Zhi-Kai Chen, Jun-Jie Tao, Wei-Xiang Mao +2
The efficiency of Large Language Model (LLM) serving is fundamentally limited by the sequential nature of autoregressive decoding. Speculative Decoding (SD) mitigates this by using…
BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
Lan Li, Tao Hu, Da-Wei Zhou +3
Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transfe…
HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning
Zhen-Hao Xie, Yan Wang, Lan Li +3
Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-trained vision-language models (e.g.,…
TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering
An-Yang Ji, Jun-Peng Jiang, De-Chuan Zhan +1
Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregation. However, a common class of…
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
Zhi-Kai Chen, Jun-Peng Jiang, Jun-Jie Tao +2
Users increasingly expect image generation models to quickly adapt to highly diverse and personalized requirements, such as producing images with distinctive styles or characterist…