52 citations · 61 across the 15 of their papers we have counts for
12 papers · 1 filter
PReM: Learning What to Preserve and When to Refresh for Context Compression
Bohan Yu, Lei Shen, Chenxi Zhou +5
Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing comp…
TVIR: Building Deep Research Agents Towards Text-Visual Interleaved Report Generation
Xinkai Ma, Zhiqi Bai, Dingling Zhang +21
Deep Research Agents have shown strong capability in multi-step information retrieval, reasoning, and long-form report generation, but existing benchmarks and systems remain predom…
YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference
You Wu, Ziheng Chen, Yizhen Zhang +6
Cross-layer key-value (KV) compression has been found to be effective in efficient inference of large language models (LLMs). Although they reduce the memory consumption of the KV…
Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
Hongzhan Lin, Zhiqi Bai, Xinmiao Zhang +10
Transformer decoders have achieved strong results across tasks, but the memory required for the KV cache becomes prohibitive at long sequence lengths. Although Cross-layer KV Cache…
DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
Weize Liu, Yongchi Zhao, Yijia Luo +8
Large language models (LLMs) perform strongly on many language tasks but still struggle with complex multi-step reasoning across disciplines. Existing reasoning datasets often lack…
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Jiaheng Liu, Chenchen Zhang, Jinyang Guo +13
Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distil…