raahul thakur's picture

raahul thakur PRO

Raahulthakur
Β·

AI & ML interests

Data enthusiast pursuing a Master's in Astrophysics. Passionate about deep learning models and their applications in solving complex problems.

Recent Activity

updated a Space about 16 hours ago
Raahulthakur/FinsightX
reacted to Kseniase's post with πŸ”₯ about 17 hours 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 πŸ‘‡ If you liked this, also subscribe to the Turing Post -> https://www.turingpost.com/subscribe
View all activity

Organizations

Linguana AI's profile picture

Raahulthakur's activity

reacted to Kseniase's post with πŸ”₯ about 17 hours ago
view post
Post
1647
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 -> Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption (2504.20769)
Provides a few structured, defensive reasoning exemplars to improve the robustness of LLMs

2. Hybrid-CoT -> AdaR1: From Long-CoT to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization (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 -> T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT (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) -> Efficient Reasoning for LLMs through Speculative Chain-of-Thought (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) -> Co-CoT: A Prompt-Based Framework for Collaborative Chain-of-Thought Reasoning (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 -> Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning (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 πŸ‘‡

If you liked this, also subscribe to the Turing Post -> https://www.turingpost.com/subscribe
  • 1 reply
Β·
reacted to nyuuzyou's post with πŸ”₯ about 17 hours ago
view post
Post
1232
πŸ–ΌοΈ PublicDomainFiles.com Collection - nyuuzyou/publicdomainfiles

Collection of 206,204 Public Domain multimedia files featuring:

- Comprehensive metadata: title, description, creator name, keywords, original page URL, and more.
- Contains various media types including images, clip art, artwork, fonts, videos, and TV shows.
- All content explicitly released into the public domain under the CC0 license.
- Organized in a single train split with 206,204 entries.
reacted to CadenHolman's post with πŸ”₯ about 17 hours ago
view post
Post
1064
CodeDebugger.ai is a free suite of AI-powered tools built for developers. Instantly debug or format your code with help from advanced language models.

Code Debugger
⭐ Submit your code (supports PHP, Python, JavaScript, HTML, SQL, CSS, and more)
⭐ Receive a detailed AI-generated bug report with suggestions for improvement

Code Formatter
⭐ Submit your code (same language support)
⭐ Instantly receive clean, consistently formatted code

For both tools:
⭐ Supports virtually any programming language
⭐ No sign-up or login required
⭐ Your code is automatically deleted after 24 hours for privacy

Give it a try:
πŸ‘‰ https://CodeDebugger.ai/
reacted to samihalawa's post with πŸ”₯ about 17 hours ago
view post
Post
1331
HELLO GUYS πŸš€ Just released my first MCP: VUDA – Visual UI Debug Agent
Ever been stuck debugging buttons that don’t work? Broken flows? Inconsistent UI behavior?

VUDA sees it, clicks it, fixes it.
An automated visual debug agent that inspects, validates, and repairs your UI β€” like magic 🧠✨ Better that any other playwright / puppeteer.

πŸ”§ Install now via Smithery:

npx -y @smithery /cli@latest install @samihalawa /visual-ui-debug-agent-mcp --client cursor



βΈ»

Want a shorter alt for social media too?
reacted to their post with ❀️ about 17 hours ago
view post
Post
1619
FinSightX: Your AI Financial Co-Pilot
FinSightX is a multi-agent financial assistant powered by language models. Designed for analysts, investors, and fintech developers, it combines insights from multiple domains into a single, sleek Streamlit interface.

Features
Equity Analyst Agent β†’ Ask questions about stocks, indicators, performance.

Macro Strategist Agent β†’ Get macroeconomic insights using language models.
News Summarizer Agent β†’ Summarizes market headlines instantly.
Quant Backtester Agent β†’ Run basic backtests using bt.
Regulatory Radar Agent β†’ Monitor policy shifts and alerts.
Client Advisor Agent β†’ Assist with client queries or hypothetical portfolios.

Tech Stack
transformers, sentence-transformers
torch, scikit-learn, neuralprophet
bt for strategy backtesting
chromadb for vector storage
Streamlit + FastAPI for UI/backend

Developed and maintained by @Raahul-Thakur
Live Space: Raahulthakur/FinsightX

Built using open-source tools and financial domain knowledge. Contributions, feedback, and forks welcome!
posted an update about 17 hours ago
view post
Post
1619
FinSightX: Your AI Financial Co-Pilot
FinSightX is a multi-agent financial assistant powered by language models. Designed for analysts, investors, and fintech developers, it combines insights from multiple domains into a single, sleek Streamlit interface.

Features
Equity Analyst Agent β†’ Ask questions about stocks, indicators, performance.

Macro Strategist Agent β†’ Get macroeconomic insights using language models.
News Summarizer Agent β†’ Summarizes market headlines instantly.
Quant Backtester Agent β†’ Run basic backtests using bt.
Regulatory Radar Agent β†’ Monitor policy shifts and alerts.
Client Advisor Agent β†’ Assist with client queries or hypothetical portfolios.

Tech Stack
transformers, sentence-transformers
torch, scikit-learn, neuralprophet
bt for strategy backtesting
chromadb for vector storage
Streamlit + FastAPI for UI/backend

Developed and maintained by @Raahul-Thakur
Live Space: Raahulthakur/FinsightX

Built using open-source tools and financial domain knowledge. Contributions, feedback, and forks welcome!