Kseniase (Ksenia Se) – Community Activity

upvoted a paper about 12 hours ago

Real-World Gaps in AI Governance Research

replied to their post 1 day ago

10 new Chain-of-Thoughts (CoT) methods CoT has long been one of the hottest techniques in AI thanks to its effectiveness and compelling core idea: encouraging models to solve complex problems through explicit intermediate reasoning steps. But usually researchers modify original CoT approach, finding tips that further improve LLMs' reasoning. That's what we're going to talk about today. Here's a list of 10 latest enhanced CoT approaches: 1. Chain-of-Defensive-Thought -> https://huggingface.co/papers/2504.20769 Provides a few structured, defensive reasoning exemplars to improve the robustness of LLMs 2. Hybrid-CoT -> https://huggingface.co/papers/2504.21659 Proposes using Adaptive Hybrid Reasoning Model (AdaR1) that combines Long- and Short-CoT, and applying bi-level preference training to select effective reasoning styles 3. Semantic-level and token-level CoT -> https://huggingface.co/papers/2505.00703 Introduces T2I-R1 text-to-image gen model, that uses semantic-level CoT for prompt planning and token-level CoT for pixel-level generation, while BiCoT-GRPO coordinates them both 4. Speculative CoT (SCoT) -> https://huggingface.co/papers/2504.19095 SCoT drafts multiple reasoning paths with a lightweight draft, selects the best, and uses the target model for correction - all this to reduce latency by 48–66% 5. Collaborative CoT (Co-CoT) -> https://huggingface.co/papers/2504.17091 Breaks reasoning into blocks that users can inspect, modify and re-run, promoting active engagement. An adaptation mechanism aligns outputs with diverse cognitive styles and user goals 6. XS-CoT -> https://huggingface.co/papers/2504.20835 It's a cross-lingual framework that integrates speech-to-text translation into reasoning, using a semi-implicit CoT approach to compress intermediate tokens. This improves non-core language responses by up to 45% Read further in the comments 👇 If you liked this, also subscribe to the Turing Post -> https://www.turingpost.com/subscribe

posted an update 1 day ago

10 new Chain-of-Thoughts (CoT) methods CoT has long been one of the hottest techniques in AI thanks to its effectiveness and compelling core idea: encouraging models to solve complex problems through explicit intermediate reasoning steps. But usually researchers modify original CoT approach, finding tips that further improve LLMs' reasoning. That's what we're going to talk about today. Here's a list of 10 latest enhanced CoT approaches: 1. Chain-of-Defensive-Thought -> https://huggingface.co/papers/2504.20769 Provides a few structured, defensive reasoning exemplars to improve the robustness of LLMs 2. Hybrid-CoT -> https://huggingface.co/papers/2504.21659 Proposes using Adaptive Hybrid Reasoning Model (AdaR1) that combines Long- and Short-CoT, and applying bi-level preference training to select effective reasoning styles 3. Semantic-level and token-level CoT -> https://huggingface.co/papers/2505.00703 Introduces T2I-R1 text-to-image gen model, that uses semantic-level CoT for prompt planning and token-level CoT for pixel-level generation, while BiCoT-GRPO coordinates them both 4. Speculative CoT (SCoT) -> https://huggingface.co/papers/2504.19095 SCoT drafts multiple reasoning paths with a lightweight draft, selects the best, and uses the target model for correction - all this to reduce latency by 48–66% 5. Collaborative CoT (Co-CoT) -> https://huggingface.co/papers/2504.17091 Breaks reasoning into blocks that users can inspect, modify and re-run, promoting active engagement. An adaptation mechanism aligns outputs with diverse cognitive styles and user goals 6. XS-CoT -> https://huggingface.co/papers/2504.20835 It's a cross-lingual framework that integrates speech-to-text translation into reasoning, using a semi-implicit CoT approach to compress intermediate tokens. This improves non-core language responses by up to 45% Read further in the comments 👇 If you liked this, also subscribe to the Turing Post -> https://www.turingpost.com/subscribe

Ksenia Se

AI & ML interests

Recent Activity

Organizations

Kseniase's activity

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking