1 188 687

Motoki Wu PRO

tokestermw

https://motoki.co

AI & ML interests

None yet

Recent Activity

upvoted an article 1 day ago

Saying Thank You to a LLM Isn't Free — Measuring the Energy Cost of Politeness

liked a model 4 days ago

mistralai/Mistral-Small-24B-Base-2501

liked a Space 4 days ago

hexgrad/Kokoro-TTS

View all activity

Organizations

tokestermw's activity

upvoted an article 1 day ago

Article

Saying Thank You to a LLM Isn't Free — Measuring the Energy Cost of Politeness

and 2 others •

4 days ago

• 8

upvoted 2 papers 6 days ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published 6 days ago • 204

Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs

Paper • 2506.05629 • Published 10 days ago • 33

upvoted an article 8 days ago

Article

Making Gemma 3 think

•

Mar 13

• 10

upvoted a paper 8 days ago

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design

Paper • 2506.04734 • Published 11 days ago • 19

upvoted a paper 11 days ago

From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval

Paper • 2505.23059 • Published 18 days ago • 13

upvoted an article 12 days ago

Article

Context Is Gold to Find the Gold Passage: Evaluating and Training Contextual Document Embeddings

and 1 other •

14 days ago

• 23

upvoted a paper 13 days ago

Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

Paper • 2505.20322 • Published 23 days ago • 14

upvoted a paper 16 days ago

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

Paper • 2505.20355 • Published 21 days ago • 36

upvoted a paper 18 days ago

s3: You Don't Need That Much Data to Train a Search Agent via RL

Paper • 2505.14146 • Published 27 days ago • 17

upvoted a paper 20 days ago

Distilling LLM Agent into Small Models with Retrieval and Code Tools

Paper • 2505.17612 • Published 24 days ago • 77

upvoted 2 papers 25 days ago

Think Only When You Need with Large Hybrid-Reasoning Models

Paper • 2505.14631 • Published 26 days ago • 19

Reward Reasoning Model

Paper • 2505.14674 • Published 26 days ago • 35

upvoted 2 papers 26 days ago

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning

Paper • 2505.13866 • Published 27 days ago • 16

Improving Assembly Code Performance with Large Language Models via Reinforcement Learning

Paper • 2505.11480 • Published about 1 month ago • 8

upvoted 2 papers 27 days ago

AdaptThink: Reasoning Models Can Learn When to Think

Paper • 2505.13417 • Published 27 days ago • 78

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Paper • 2505.11896 • Published 30 days ago • 57

upvoted 3 papers about 1 month ago

System Prompt Optimization with Meta-Learning

Paper • 2505.09666 • Published May 14 • 70

Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models

Paper • 2505.10554 • Published May 15 • 119

Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning

Paper • 2505.01441 • Published Apr 28 • 36

Motoki Wu PRO

AI & ML interests

Recent Activity

Organizations

tokestermw's activity

Saying Thank You to a LLM Isn't Free — Measuring the Energy Cost of Politeness

Making Gemma 3 think

*Context Is Gold to Find the Gold Passage*: Evaluating and Training Contextual Document Embeddings

Context Is Gold to Find the Gold Passage: Evaluating and Training Contextual Document Embeddings