Task-specific LoRA adapters offer a modular way to specialize large language and vision-language models. However, existing adapter composition methods are mostly static and cannot adapt to individual test inputs. To address these issues, we propose \textbf{LiST}, a label-free test-time LoRA fusion framework that conver...
Yi-Hua Shao, Jia Li, Si-Yu Chen et al.· 2 citations
The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently. Despite great success achieved, existing retrieval-based memory approaches typically overlook the differences between memories and employ a unified strategy to process all memories, leading to suboptimal performance. Th...
Yi Wen, De-Rong Xu, Peng-Yue Jia et al.· 0 citations
Out-of-distribution (OOD) generalization in industrial Model-as-a-Service (MaaS) systems is often hindered by a trilemma of heterogeneous distribution shifts, strict inference latency budgets, and rigorous privacy constraints. Traditional robust learning and emerging foundation models frequently struggle with the entan...
Qi Qin, Yuzhao Zhang, Jiaxing Han et al.· Proceedings of the 32nd ACM...· 0 citations
The contribution is a system-level integration that makes long-term, multi-interest, and multimodal modeling jointly deployable in a real-time production pipeline, together with the engineering practices required to sustain it.
Yong-Kang Fu, Bei-Ning Bao, Yu Jiang et al.· 0 citations
Results show that UNIQUE provides a stable, efficient, and production-ready framework for unified retrieval and ranking in industrial recommendation, and a balanced quantization mechanism is further introduced to mitigate codebook imbalance and improve long-tail representation.
Zhuang-Chen-Ying-Ying Liu, Yong-Kang Fu, Zuo-Dong Yang et al.· Proceedings of the 20th ACM...· 0 citations
The proliferation of social media has created fertile ground for misinformation, a challenge further intensified by recent advances in generative artificial intelligence. Modern fake news increasingly takes the form of sophisticated multimodal campaigns, where synthetic images and stylistically manipulated text are joi...
Mao-Lin Wang, Ziting Mai, Zi-Chun Liu et al.· Proceedings of the 32nd ACM...· 0 citations
Inspired by Multiple-Trace Theory in cognitive psychology, this work revisit long video understanding from a probe-echo perspective, in which human episodic memories are activated and integrated in parallel, and proposes ProEchoMem, a cognitive-inspired framework that simulates the probe-echo mechanism.
Derong Xu, Yanxin Chen, Wanyu Wang et al.· Annual International ACM SIG...· 0 citations
A lightweight training framework that learns a single Behavior-Equivalent Token that substantially reduces inference cost and frees nearly the entire context window for user inputs and model outputs.
Jiancheng Dong, Pengyue Jia, Jingyu Peng et al.· 2 citations
TRACE is presented, a query processing framework over temporal evidence graphs for evolving conversational data that separates lexical recall from evidence reconstruction, enabling bounded query-time reasoning over long conversational histories.
Maolin Wang, Yu Wang, Zichun Liu et al.· 0 citations
DAR-Lite is proposed, a serial two-stage framework that rethinks the detection pipeline through explicit decoupling of representation denoising and contextual reasoning, and achieves a favorable balance between detection performance and computational cost.
Maolin Wang, Ziting Mai, Zichun Liu et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
