Shyam Sunder Kumar's picture

Shyam Sunder Kumar

theainerd

·

AI & ML interests

Natural Language Processing

Recent Activity

reacted to Kseniase's post with 🔥 3 days ago

9 types of "Chain-of-..." approaches: Chain-of-Thought (CoT) prompting enhances reasoning in AI models by breaking down complex problems into step-by-step logical sequences. It continues proving its effectiveness, especially in top-performing reasoning models. However, there are other similar methods, that expand CoT and can be used for different purposes. Here are 9 of them: 1. Chain-of-Action-Thought (COAT) -> https://huggingface.co/papers/2502.02508 Helps model decide when to keep thinking, double-check their work, or try a different approach, using special guiding tokens. 2. Chain of Draft (CoD) -> https://huggingface.co/papers/2502.18600 It helps model generate short but meaningful reasoning steps, cutting costs and making processing faster 3. Chain-of-Agents -> https://huggingface.co/papers/2406.02818 Uses multi-agent collaboration: Worker agents process text parts in a structured chain, and manager agent summarizes the results 4. Chain-of-RAG ->https://huggingface.co/papers/2501.14342 Creates retrieval chains, instead of retrieving all info at once. It can dynamically adjust its search process and its parameters like step number 5. Chain-of-Shot Prompting (CoS) -> https://huggingface.co/papers/2502.06428 Helps models pick frames crucial for understanding a video, using a binary video summary and video co-reasoning module. 6. Chain of Hindsight (CoH) -> https://huggingface.co/papers/2302.02676 Converts all feedback into sequences to fine-tune the model and refine outputs 7. Chain-of-Note (CoN) -> https://huggingface.co/papers/2311.09210 Generates sequential reading notes for each retrieved document to assess relevance before integrating info into the final answer 8. Chain of Diagnosis (CoD) -> https://huggingface.co/papers/2407.13301 Transforms the diagnostic process into a diagnostic chain 9. Chain(s)-of-Knowledge -> https://www.turingpost.com/p/cok Enhance LLMs by dynamically pulling in external knowledge to improve accuracy and reduce errors

upvoted an article 7 days ago

SigLIP 2: A better multilingual vision language encoder

reacted to AdinaY's post with 🔥 7 days ago

Wan2.1 🔥📹 new OPEN video model by Alibaba Wan team! Model: https://huggingface.co/Wan-AI/Wan2.1-T2V-14B Demo: https://huggingface.co/spaces/Wan-AI/Wan2.1 ✨Apache 2.0 ✨8.19GB VRAM, runs on most GPUs ✨Multi-Tasking: T2V, I2V, Video Editing, T2I, V2A ✨Text Generation: Supports Chinese & English ✨Powerful Video VAE: Encode/decode 1080P w/ temporal precision

View all activity

Organizations

Collections 4

models 2

theainerd/Wav2Vec2-large-xlsr-hindi

Automatic Speech Recognition • Updated May 31, 2023 • 782k • • 5

theainerd/wav2vec2-large-xlsr-53-odia

Automatic Speech Recognition • Updated Mar 24, 2021 • 1.91k • 3

datasets

None public yet