Model merging constructs multi-task models without expensive joint training but often suffers from parameter interference. Some solutions mitigate this by constraining finetuning using data from the other tasks to be merged, violating the core independence and privacy assumption of model merging. Recent work offers pre...
Shang-Ge Liu, Dan-Yue Qian, Qi Fan et al.· 0 citations
The Key-Value (KV) cache constitutes a dominant source of memory consumption during large language model (LLM) inference, particularly in long-context and complex reasoning scenarios. Existing KV cache quantization methods have explored different compression granularities, including layer-wise precision adjustment and...
Yang Zhou, Zhi-Ping Wu, Run-Chang Jiang et al.· 0 citations
Vision-language models (VLMs) face a fixed-budget trade-off between processing more visual information for fine-grained perception and using a larger language backbone for complex reasoning. Existing studies do not tell us which combination of backbone size and input resolution to deploy, especially in high-resolution...
Xinye Zhao, Yun-Kai Dang, Yun-Chen Wu et al.· 0 citations
TReVS is proposed, a training-free framework that combines textual relevance with vision-encoder saliency for pre-LLM pruning and leverages high-variance attention heads to remove task-irrelevant tokens at shallow-to-intermediate layers of the LLM.
Riemannian Geometry-Sensitive Quantization (RGSQ), which formulates quantization as a reconstruction problem under a unified Fisher-Riemannian metric, enabling standard unimodal PTQ methods to evaluate multimodal quantization error under their original assumptions.
Zhi-Ping Wu, Dong-Dong Ren, Yang Zhou et al.· 0 citations
This work proposes B rain-inspired Supervised Supervised Reflection (BUS), a label-free training framework to enhance reflective reasoning capability in challenging image analysis and validate that backward prediction capability is critical for VLM reasoning.
Jiacheng Yang, Tongying Xiao, Yun-Kai Dang et al.· 0 citations
This paper first proves that TFS is a sufficient condition for weight disentanglement, and finds that TFS also gives rise to an observable geometric consequence: weight vector orthogonality, which positions TFS as the common cause for both the desired functional outcome and a measurable geometric property.
Shan Liu, Yuehan Yin, Lei Wang et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.