Hugging Face Trending Papers
$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
Sep 30
$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient
arXiv:2609.37976v1 Announce Type: cross Abstract: LLMs trained with Chain-of-thought excel in reasoning capability, but often come with excessive token cost. We find that the core of reasoning capaci...
arXiv AI
Sep 15
Post-Reasoning: Improving the Performance of Non-Thinking Models at No Cost
arXiv:2605.06165v2 Announce Type: replace Abstract: As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contribut...
arXiv AI
Oct 1
Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression
arXiv:2510.01581v2 Announce Type: replace-cross Abstract: Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in l...
arXiv AI
Jun 2
ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks
arXiv:2606. 01080v1 Announce Type: cross Abstract: Large language models often improve on difficult tasks by spending inference-time compute on a reasoning trace before producing the final answer.
arXiv AI
Sep 23
Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models
arXiv:2609.23589v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio repr...
arXiv AI
Jul 23
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.