中文
相关论文

相关论文: Less Is More: Fast and Accurate Reasoning with Cro…

200 篇论文

The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods either sparsify the attention map with structured patterns or permanently evict tokens at…

计算与语言 · 计算机科学 2026-05-04 Dongwon Jo , Beomseok Kang , Jiwon Song , Jae-Joon Kim

Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency. Prior work typically decomposes inference into…

计算与语言 · 计算机科学 2026-04-21 Junhao Hu , Fangze Li , Mingtao Xu , Feifan Meng , Shiju Zhao , Tiancheng Hu , Ting Peng , Anmin Liu , Wenrui Huang , Chenxu Liu , Ziyue Hua , Tao Xie

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long…

Understanding and reasoning over long contexts is a crucial capability for language models (LMs). Although recent models support increasingly long context windows, their accuracy often deteriorates as input length grows. In practice, models…

计算与语言 · 计算机科学 2026-04-17 Xi Ye , Wuwei Zhang , Fangcong Yin , Howard Yen , Danqi Chen

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

机器学习 · 计算机科学 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu

The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is particularly acute for emerging agentic applications that require processing multi-million…

机器学习 · 计算机科学 2026-05-19 Ceyu Xu , Jiangnan Yu , Yongji Wu , Yuan Xie

Accommodating long sequences efficiently in autoregressive Transformers, especially within an extended context window, poses significant challenges due to the quadratic computational complexity and substantial KV memory requirements…

计算与语言 · 计算机科学 2024-06-25 Chao Lou , Zixia Jia , Zilong Zheng , Kewei Tu

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

计算与语言 · 计算机科学 2025-06-24 Kang Chen , Mengdi Zhang , Yixin Cao

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

机器学习 · 计算机科学 2025-05-27 Dan Peng , Zhihui Fu , Zewen Ye , Zhuoran Song , Jun Wang

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

机器学习 · 计算机科学 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

While Chain-of-Thought (CoT) prompting improves reasoning in large language models (LLMs), the excessive length of reasoning tokens increases latency and KV cache memory usage, and may even truncate final answers under context limits. We…

计算与语言 · 计算机科学 2025-05-26 Gengyang Li , Yifeng Gao , Yuming Li , Yunfang Wu

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs significant…

计算与语言 · 计算机科学 2026-02-04 Michael Hassid , Gabriel Synnaeve , Yossi Adi , Roy Schwartz

Large Language Models (LLMs) excel at reasoning, traditionally requiring high-quality large-scale data and extensive training. Recent works reveal a very appealing Less-Is-More phenomenon where very small, carefully curated high-quality…

机器学习 · 计算机科学 2026-04-22 Rapheal Huang , Weilong Guo

Reasoning-capable large language models (LLMs) achieve strong performance on complex tasks but often exhibit overthinking after distillation, generating unnecessarily long chain-of-thought (CoT) reasoning even for simple inputs and…

Recent research enhances language model reasoning by scaling test-time compute via longer chain-of-thought traces. This often improves accuracy but also introduces redundancy and high computational cost, especially for small language models…

机器学习 · 计算机科学 2025-05-26 Xuechen Zhang , Zijian Huang , Chenshun Ni , Ziyang Xiong , Jiasi Chen , Samet Oymak

Accelerating large language model (LLM) inference is critical for real-world deployments requiring high throughput and low latency. Contextual sparsity, where each token dynamically activates only a small subset of the model parameters,…

机器学习 · 计算机科学 2025-11-13 Susav Shrestha , Brad Settlemyer , Nikoli Dryden , Narasimha Reddy

Recent large language models have shown promising capabilities in long-form reasoning, following structured chains of thought before arriving at a final answer. However, we observe that these reasoning paths tend to include substantial…

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

计算与语言 · 计算机科学 2026-05-05 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become…

DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the…

计算机视觉与模式识别 · 计算机科学 2023-07-25 Dehua Zheng , Wenhui Dong , Hailin Hu , Xinghao Chen , Yunhe Wang
‹ 上一页 1 2 3 10 下一页 ›