AMD AI DevMaster Hackathon
β’ 3
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
Post
3388
Open sourcing Coala Embeddings! It can compress 20 million documents which can take 80gb ram down to just 1gb RAM.
Why is this important? Embeddings are used everywhere(RAG, semantic search, etc.) by many.
Coala Embeddings massively cheapen cost to host them while being simply and easy to use.
GitHub: https://github.com/ysharma3501/CoalaEmbeddings
Notebook Demo: https://colab.research.google.com/drive/1TXip-vZg72e_2AB185MINufVVav8Oo9T?usp=sharing
Why is this important? Embeddings are used everywhere(RAG, semantic search, etc.) by many.
Coala Embeddings massively cheapen cost to host them while being simply and easy to use.
GitHub: https://github.com/ysharma3501/CoalaEmbeddings
Notebook Demo: https://colab.research.google.com/drive/1TXip-vZg72e_2AB185MINufVVav8Oo9T?usp=sharing
charyanghfΒ
published an article about 1 month ago
Article
AMD AI DevMaster Hackathon
LeRobot-worldwide-hackathon
β’ β’ 3
lilkmΒ
published a
dataset 3 months ago
rajkumarrawalΒ
submitted a
paper to Daily Papers 3 months ago
rajkumarrawalΒ
posted an update 3 months ago
Post
2158
LLMs arenβt just answering questions anymore, theyβre learning to evolve. Self evolving AI is the true endgame.
AI has shifted from short tasks to long missions. The breakthrough isnβt just automation, itβs machines learning human methods and applying them at machine speed. From cybersecurity to finance, from OPCs to NPCs, the wave is irreversible.
Read the full article: Self Evolving is the Endgame or final destiny
https://huggingface.co/blog/rajkumarrawal/self-evolving-is-the-endgame-or-final-destiny
Whatβs your definition of true AGI? Comment below.
AI has shifted from short tasks to long missions. The breakthrough isnβt just automation, itβs machines learning human methods and applying them at machine speed. From cybersecurity to finance, from OPCs to NPCs, the wave is irreversible.
Read the full article: Self Evolving is the Endgame or final destiny
https://huggingface.co/blog/rajkumarrawal/self-evolving-is-the-endgame-or-final-destiny
Whatβs your definition of true AGI? Comment below.
- 1 reply
rajkumarrawalΒ
posted an update 4 months ago
Post
235
I submitted a "Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization" Paper by Zi-Bo Qin, Feng-Feng Wei, Tai-You Chen, Wei-Neng Chen to Daily Papers on huggingface.
A trajectory-driven framework uses large language models to guide agent behavior and cooperation patterns in distributed black-box consensus optimization, improving solution quality and efficiency.
Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization (2605.00691)
A trajectory-driven framework uses large language models to guide agent behavior and cooperation patterns in distributed black-box consensus optimization, improving solution quality and efficiency.
Learning to Act and Cooperate for Distributed Black-Box Consensus Optimization (2605.00691)
rajkumarrawalΒ
submitted a
paper to Daily Papers 4 months ago
Sri-Vigneshwar-DJΒ
posted an update 4 months ago
Post
180
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) β 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** Β· GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
β Info-extraction: **0.942**
β Knowledge-update: **0.714**
β Multi-session: **0.606**
β Temporal: **0.477** β the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense Β· adaptive temporal decay Β· embedded (no server) Β· p50 = 0.19ms Β· MIT
Raw results + audit JSONs: Hawky-ai/longmemeval-results
We ran Feather DB v0.8.0 on LongMemEval (ICLR 2025) β 500 questions across real multi-session conversations, up to 115K tokens each.
**Score: 0.693** Β· GPT-4o full-context baseline: 0.640
Full 500-question run with Gemini-Flash: **$2.40**
Per-axis breakdown:
β Info-extraction: **0.942**
β Knowledge-update: **0.714**
β Multi-session: **0.606**
β Temporal: **0.477** β the hard one, Phase 9 addresses this
Architecture: Hybrid BM25+dense Β· adaptive temporal decay Β· embedded (no server) Β· p50 = 0.19ms Β· MIT
pip install feather-dbRaw results + audit JSONs: Hawky-ai/longmemeval-results
rajkumarrawalΒ
posted an update 4 months ago
Post
1586
I submitted a "Context-Value-Action Architecture for Value-Driven Large Language Model Agents" Paper by TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang Zhiqiang Wu Guojie SongΒ· From 
PekingUniversity to Daily Papers on 
huggingface .
Large language models exhibit behavioral rigidity that worsens with intensified reasoning, prompting the development of a Context-Value-Action architecture that decouples action generation from cognitive reasoning using a Value Verifier trained on human data.
Context-Value-Action Architecture for Value-Driven Large Language Model Agents (2604.05939)
Large language models exhibit behavioral rigidity that worsens with intensified reasoning, prompting the development of a Context-Value-Action architecture that decouples action generation from cognitive reasoning using a Value Verifier trained on human data.
Context-Value-Action Architecture for Value-Driven Large Language Model Agents (2604.05939)
rajkumarrawalΒ
submitted a
paper to Daily Papers 4 months ago
Post
3282
Just open sourced LavaSR v2: a model that can enhance 5000 seconds of audio in 1 second while being higher quality than giant and slow 6gb diffusion models!
It works with any sampling rate from 8-48khz and is nearly 5000x faster than competition while being superior in objective benchmarks.
LavaSR v2 is Perfect for
- Enhancing TTS models.
- Fixing old audio datasets.
- Restoring low quality recordings.
You can check out the examples and run it locally or online:
Repo: https://github.com/ysharma3501/LavaSR.git
Demo: YatharthS/LavaSR
Model: YatharthS/LavaSR
It works with any sampling rate from 8-48khz and is nearly 5000x faster than competition while being superior in objective benchmarks.
LavaSR v2 is Perfect for
- Enhancing TTS models.
- Fixing old audio datasets.
- Restoring low quality recordings.
You can check out the examples and run it locally or online:
Repo: https://github.com/ysharma3501/LavaSR.git
Demo: YatharthS/LavaSR
Model: YatharthS/LavaSR
rajkumarrawalΒ
posted an update 7 months ago
Post
235
I submitted a "Continual GUI Agents" Paper by Ziwei Liu, Borul Kang, Hangjie Yuan, Zixiang Zhao, Wei li, Yifan Zhu, Tao Feng ,
From
Tsinghua , 
ZhejiangUniversity , 
ethz , 
BUPT2023213296 . to Daily Papers on huggingface .
Continual GUI Agents framework addresses performance degradation in dynamic digital environments through reinforcement fine tuning with novel anchoring rewards that stabilize learning across shifting UI domains and resolutions.
Continual GUI Agents (2601.20732)
From
Continual GUI Agents framework addresses performance degradation in dynamic digital environments through reinforcement fine tuning with novel anchoring rewards that stabilize learning across shifting UI domains and resolutions.
Continual GUI Agents (2601.20732)
Sri-Vigneshwar-DJΒ
posted an update 7 months ago
Post
1472
Just released a new dataset designed for training reasoning models on Meta (Facebook/Instagram) advertising fatigue detection!
What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:
π Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
π©Ί Performance Diagnosis: Root cause analysis frameworks
π Strategy: Creative refresh cadence, testing frameworks
π Analysis: ROI calculations, metric interpretation
Why GRPO? GRPO training helps models learn structured reasoning. Each response follows the <thinking> and <answer> format.
Check it out here: Sri-Vigneshwar-DJ/meta-fatigue-grpo-dataset
What is it? A GRPO (Group Relative Policy Optimization) training dataset with 200+ carefully crafted scenarios covering:
π Fatigue Signal Detection: CTR drops, CPM spikes, frequency analysis
π©Ί Performance Diagnosis: Root cause analysis frameworks
π Strategy: Creative refresh cadence, testing frameworks
π Analysis: ROI calculations, metric interpretation
Why GRPO? GRPO training helps models learn structured reasoning. Each response follows the <thinking> and <answer> format.
Check it out here: Sri-Vigneshwar-DJ/meta-fatigue-grpo-dataset
rajkumarrawalΒ
posted an update 7 months ago
Post
3701
I submitted a "FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning" Paper by Tanyu Chen, Tairan Chen, Kai shen , Zhenghua Bao, Zhihui Zhang, Man Yuan, Yi Shi From 
FlashLabs to Daily Papers on huggingface .
Chroma 1.0 enables real time spoken dialogue with personalized voice cloning through discrete speech representations and interleaved text audio token scheduling.
Chroma 1.0 , the worldβs first open source, real time speech to speech model with voice cloning.
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning (2601.11141)
Chroma 1.0 enables real time spoken dialogue with personalized voice cloning through discrete speech representations and interleaved text audio token scheduling.
Chroma 1.0 , the worldβs first open source, real time speech to speech model with voice cloning.
FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning (2601.11141)
rajkumarrawalΒ
submitted a
paper to Daily Papers 7 months ago
BeegbrainΒ
authored 2
papers 7 months ago
BeegbrainΒ
submitted 2
papers to Daily Papers 7 months ago
Sri-Vigneshwar-DJΒ
posted an update 7 months ago
Post
249
ποΈ Hugging Face Community Post
Title: 𧬠Experimenting with "Dynamic Chaos" in Tamil SLMs
Hi everyone! I just published a new experimental study on Small Language Model (SLM) resilience.
I took the Qwen2.5-0.5B model and put it through a "Chaos Phase" to see how much weight data a tiny model can lose before its understanding of classical Tamil grammar breaks.
Key highlights of the study:
Target Data: Fine-tuned on the Thirukkural (1,330 couplets + modern explanations).
The Chaos Step: Applied 20% random weight pruning but implemented "Layer Protection" for the Token Embeddings and LM Head to keep the characters readable.
Compression: 4-bit (Q4_K_M) quantization for extreme efficiency.
Result: A surrealist classical Tamil model that is ultra-light (~300MB) and ultra-fast!
Check out the model and the experiment logic here: Sri-Vigneshwar-DJ/qwen-tamil-chaos-v1
Title: 𧬠Experimenting with "Dynamic Chaos" in Tamil SLMs
Hi everyone! I just published a new experimental study on Small Language Model (SLM) resilience.
I took the Qwen2.5-0.5B model and put it through a "Chaos Phase" to see how much weight data a tiny model can lose before its understanding of classical Tamil grammar breaks.
Key highlights of the study:
Target Data: Fine-tuned on the Thirukkural (1,330 couplets + modern explanations).
The Chaos Step: Applied 20% random weight pruning but implemented "Layer Protection" for the Token Embeddings and LM Head to keep the characters readable.
Compression: 4-bit (Q4_K_M) quantization for extreme efficiency.
Result: A surrealist classical Tamil model that is ultra-light (~300MB) and ultra-fast!
Check out the model and the experiment logic here: Sri-Vigneshwar-DJ/qwen-tamil-chaos-v1