paper-with-me

Papers

InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context

2026-03-05 · Xin Teng, Canyu Zhang, Shaoyi Zheng, Danyang Zhuo, Tianyi Zhou, Shenji Wan arxiv

Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts. A common strategy is to precompute key-value (KV) caches for individual documents and selectively recompute a small subset of tokens to restore global causal dependencies, but existing methods rely on heuristics or representation discrepancies without modeling whether selected tokens can effectively influence generation. We cast selective KV recomputation as an information flow problem and show that a simple attention-norm signal from the query reliably identifies tokens that are both semantically relevant and structurally positioned to propagate information, when computed under an inference-consistent RoPE geometry. We therefore reconstruct global positional assignments for retrieved chunks and introduce an information-flow-guided chunk reordering strategy. Experiments on Large Language Model and Vision-Language Model benchmarks demonstrate consistent gains over prior methods under comparable latency.

📄 PDF Abstract BibTeX arXiv:2603.05353

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

InfoFlowNet: A Multi-head Attention-based Self-supervised Learning Model with Surrogate Approach for Uncovering Brain Effective Connectivity

2023-11-30 · Chun-Hsiang Chuang, Shao-Xun Fang, Chih-Sheng Huang, Weiping Ding

Deciphering brain network topology can enhance the depth of neuroscientific knowledge and facilitate the development of neural engineering methods. Effective connectivity, a measure of brain network dynamics, is particul…

Causal DiscoveryCausal InferenceEEGElectroencephalogram (EEG)+2

InfoFlow: Reinforcing Search Agent Via Reward Density Optimization

2025-10-30 · Kun Luo, Hongjin Qian, Zheng Liu, Ziyi Xia 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising approach for enhancing agentic deep search. However, its application is often hindered by low \textbf{Reward Density} in deep search scenarios, where a…

Reinforcement Learning

InfoFlow: A Framework for Multi-Layer Transformer Analysis

2026-05-18 · Penghao Yu, Haotian Jiang, Zeyu Bao, Qianxiao Li arxiv

While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of the multi-layer setting remains limited. In this work, we establish …

AgentDecarbonizer: Carbon-Aware Execution for AI Agents

2026-08-20 · Leyi Yan, Shuangning Li, Sihang Liu arxiv

AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, invoke tools, and interact with external environments. These workflows …

Optimizing Large Model Training through Overlapped Activation Recomputation

2024-06-13 · Ping Chen, Wenjie Zhang, Shuibing He, Weijian Chen 외

Large model training often uses recomputation to alleviate memory pressure and pipelines to exploit the parallelism of data, tensors, and devices. However, existing recomputation approaches may incur high overhead when t…

modelScheduling