Rajkumar rawal PRO
rajkumarrawal
AI & ML interests
AI & Blockchain & Robotics
Recent Activity
upvoted a paper about 23 hours ago
RLDX-1 Technical Report repliedto their post 1 day ago
LLMs aren’t just answering questions anymore, they’re learning to evolve. Self evolving AI is the true endgame.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s 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
What’s your definition of true AGI? Comment below.
reacted to theirpost with 🚀 2 days ago
LLMs aren’t just answering questions anymore, they’re learning to evolve. Self evolving AI is the true endgame.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s 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
What’s your definition of true AGI? Comment below.
Organizations
replied to their post 1 day ago
reacted to their post with 🚀 2 days ago
Post
1448
LLMs aren’t just answering questions anymore, they’re learning to evolve. Self evolving AI is the true endgame.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s 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
What’s your definition of true AGI? Comment below.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s 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
What’s your definition of true AGI? Comment below.
- 1 reply
posted an update 2 days ago
Post
1448
LLMs aren’t just answering questions anymore, they’re learning to evolve. Self evolving AI is the true endgame.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s 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
What’s your definition of true AGI? Comment below.
AI has shifted from short tasks to long missions. The breakthrough isn’t just automation, it’s 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
What’s your definition of true AGI? Comment below.
- 1 reply
reacted to their post with 🚀 10 days ago
Post
206
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)
posted an update 10 days ago
Post
206
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)
reacted to their post with 🚀 about 1 month ago
Post
1574
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 Song· 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)
posted an update about 1 month ago
Post
1574
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 Song· 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)
reacted to their post with 👍 about 1 month ago
Post
227
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)
posted an update 3 months ago
Post
227
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)
reacted to their post with 👍 3 months ago
Post
3691
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 world’s 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 world’s 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)
posted an update 3 months ago
Post
3691
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 world’s 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 world’s 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)
reacted to their post with 👍 4 months ago
Post
864
I submitted a "AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts" Paper by @weizhihao1KeyuLi Junhao shi @dqwangDequan Wang @YangXiao-nlpYang Xiao Mohan Jiang @Sunshine279Jie Sun Yunze Wu Shijie Xia Xiaojie Cai Tianze Xu Weiye Si Wenjie Li Pengfei Liu From 
SJTU Shanghai Jiao Tong University 
PolyUHK The Hong Kong Polytechnic University GAIRSII-GAIR to Daily Papers on huggingfaceHugging Face.
A potentially another direction for Benchmarking the Frontiers of Autonomous Agents in 2026
Some of the observations founded are :-
-- Long-horizon tasks remain challenging :
Even frontier models struggle with sustained reasoning over real world tasks that require 1M tokens and 90 tool calls, indicating limits in long context autonomy.
-- Proprietary models outperform open source models:
Closed source models achieve a higher average score (48.4%) than open source counterparts (32.1%), revealing a persistent performance gap on complex agentic tasks.
-- Feedback driven self correction varies widely:
Models like GPT 5.2 and Claude show strong gains from iterative feedback, while others (e.g. DeepSeek V3.2) exhibit minimal or no improvement after feedback.
-- Efficiency trade offs are significant:
High performing models often consume far more tokens and time, some models (e.g. Grok 4.1 Fast) are more token efficient despite lower absolute scores.
-- Agentic scaffolds strongly influence performance:
Models tend to perform best within their native or optimized ecosystems, highlighting that agent performance depends on tight coupling between the model and its scaffold not the model alone.
..... many more...
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2601.11044)
A potentially another direction for Benchmarking the Frontiers of Autonomous Agents in 2026
Some of the observations founded are :-
-- Long-horizon tasks remain challenging :
Even frontier models struggle with sustained reasoning over real world tasks that require 1M tokens and 90 tool calls, indicating limits in long context autonomy.
-- Proprietary models outperform open source models:
Closed source models achieve a higher average score (48.4%) than open source counterparts (32.1%), revealing a persistent performance gap on complex agentic tasks.
-- Feedback driven self correction varies widely:
Models like GPT 5.2 and Claude show strong gains from iterative feedback, while others (e.g. DeepSeek V3.2) exhibit minimal or no improvement after feedback.
-- Efficiency trade offs are significant:
High performing models often consume far more tokens and time, some models (e.g. Grok 4.1 Fast) are more token efficient despite lower absolute scores.
-- Agentic scaffolds strongly influence performance:
Models tend to perform best within their native or optimized ecosystems, highlighting that agent performance depends on tight coupling between the model and its scaffold not the model alone.
..... many more...
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2601.11044)
- 1 reply
replied to their post 4 months ago
posted an update 4 months ago
Post
864
I submitted a "AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts" Paper by @weizhihao1KeyuLi Junhao shi @dqwangDequan Wang @YangXiao-nlpYang Xiao Mohan Jiang @Sunshine279Jie Sun Yunze Wu Shijie Xia Xiaojie Cai Tianze Xu Weiye Si Wenjie Li Pengfei Liu From SJTU Shanghai Jiao Tong University PolyUHK The Hong Kong Polytechnic University GAIRSII-GAIR to Daily Papers on huggingfaceHugging Face.
A potentially another direction for Benchmarking the Frontiers of Autonomous Agents in 2026
Some of the observations founded are :-
-- Long-horizon tasks remain challenging :
Even frontier models struggle with sustained reasoning over real world tasks that require 1M tokens and 90 tool calls, indicating limits in long context autonomy.
-- Proprietary models outperform open source models:
Closed source models achieve a higher average score (48.4%) than open source counterparts (32.1%), revealing a persistent performance gap on complex agentic tasks.
-- Feedback driven self correction varies widely:
Models like GPT 5.2 and Claude show strong gains from iterative feedback, while others (e.g. DeepSeek V3.2) exhibit minimal or no improvement after feedback.
-- Efficiency trade offs are significant:
High performing models often consume far more tokens and time, some models (e.g. Grok 4.1 Fast) are more token efficient despite lower absolute scores.
-- Agentic scaffolds strongly influence performance:
Models tend to perform best within their native or optimized ecosystems, highlighting that agent performance depends on tight coupling between the model and its scaffold not the model alone.
..... many more...
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2601.11044)
A potentially another direction for Benchmarking the Frontiers of Autonomous Agents in 2026
Some of the observations founded are :-
-- Long-horizon tasks remain challenging :
Even frontier models struggle with sustained reasoning over real world tasks that require 1M tokens and 90 tool calls, indicating limits in long context autonomy.
-- Proprietary models outperform open source models:
Closed source models achieve a higher average score (48.4%) than open source counterparts (32.1%), revealing a persistent performance gap on complex agentic tasks.
-- Feedback driven self correction varies widely:
Models like GPT 5.2 and Claude show strong gains from iterative feedback, while others (e.g. DeepSeek V3.2) exhibit minimal or no improvement after feedback.
-- Efficiency trade offs are significant:
High performing models often consume far more tokens and time, some models (e.g. Grok 4.1 Fast) are more token efficient despite lower absolute scores.
-- Agentic scaffolds strongly influence performance:
Models tend to perform best within their native or optimized ecosystems, highlighting that agent performance depends on tight coupling between the model and its scaffold not the model alone.
..... many more...
AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts (2601.11044)
- 1 reply
reacted to their post with 👍 4 months ago
Post
675
"Recursive Language Models" Paper become "3rd Paper of the day" on Hugging Face
Recursive Language Models (2512.24601)
Recursive Language Models (2512.24601)
posted an update 4 months ago
Post
675
"Recursive Language Models" Paper become "3rd Paper of the day" on Hugging Face
Recursive Language Models (2512.24601)
Recursive Language Models (2512.24601)
reacted to YatharthS's post with 👍 5 months ago
Post
3698
🤯 🤯 Released a high quality finetuned LLM based TTS model that can generate realistic and clear 48khz audio at over 100x realtime speed! 🤯 🤯
Github link: https://github.com/ysharma3501/MiraTTS
Model link: https://github.com/ysharma3501/MiraTTS
Blog explaining llm tts models: https://huggingface.co/blog/YatharthS/llm-tts-models
Github link: https://github.com/ysharma3501/MiraTTS
Model link: https://github.com/ysharma3501/MiraTTS
Blog explaining llm tts models: https://huggingface.co/blog/YatharthS/llm-tts-models
- 4 replies
reacted to danielhanchen's post with 👍 5 months ago
Post
5592
NVIDIA releases Nemotron 3 Nano, a new 30B hybrid reasoning model! 🔥
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
💚 Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
Has 1M context window & best in class performance for SWE-Bench, reasoning & chat. Run the MoE model locally with 24GB RAM.
GGUF: unsloth/Nemotron-3-Nano-30B-A3B-GGUF
💚 Step-by-step Guide: https://docs.unsloth.ai/models/nemotron-3
- 1 reply
reacted to danielhanchen's post with 👍 5 months ago
Post
2500
Google releases FunctionGemma, a new 270M parameter model that runs on just 0.5 GB RAM.✨
Built for tool-calling, run locally on your phone at 50+ tokens/s, or fine-tune with Unsloth & deploy to your phone.
GGUF: unsloth/functiongemma-270m-it-GGUF
Docs + Notebook: https://docs.unsloth.ai/models/functiongemma
Built for tool-calling, run locally on your phone at 50+ tokens/s, or fine-tune with Unsloth & deploy to your phone.
GGUF: unsloth/functiongemma-270m-it-GGUF
Docs + Notebook: https://docs.unsloth.ai/models/functiongemma
- 2 replies
reacted to their post with 👍 5 months ago
Post
1927
" An open standardized protocol enabling communication for autonomous robots to exchange data, coordinate tasks, and collaborate in real-time environments in the age of AI ". r2r-protocol (Robot2Robot Protocol) is now officially open source! 🔓
"pip install r2r-protocol"
Whether you're a developer, researcher, or tech enthusiast, we invite you to explore, use, and contribute to the project.
🔗 Check it out here: [ https://github.com/Tech-Parivartan/r2r-protocol?tab=readme-ov-file ]
Let’s build the future together! 💡 AiParivartanResearchLab techparivartan
Documentation of the r2r-protocal : [ https://techparivartanai.notion.site/Robot-to-Robot-r2r-Protocol-1f008f0fb18780439d70e8b9bbbdb869 ]
The R2R Protocol enables seamless robot-to-robot interaction across industrial automation, swarm robotics, logistics, and multi-agent systems. It defines structured message formats, negotiation logic, discovery mechanisms, and extensible APIs.
#r2r_protocol #robot2robot_protocol #ai #aiparivartanresearchlab #techparivartan
https://huggingface.co/blog/rajkumarrawal/rawalraj
"pip install r2r-protocol"
Whether you're a developer, researcher, or tech enthusiast, we invite you to explore, use, and contribute to the project.
🔗 Check it out here: [ https://github.com/Tech-Parivartan/r2r-protocol?tab=readme-ov-file ]
Let’s build the future together! 💡
Documentation of the r2r-protocal : [ https://techparivartanai.notion.site/Robot-to-Robot-r2r-Protocol-1f008f0fb18780439d70e8b9bbbdb869 ]
The R2R Protocol enables seamless robot-to-robot interaction across industrial automation, swarm robotics, logistics, and multi-agent systems. It defines structured message formats, negotiation logic, discovery mechanisms, and extensible APIs.
#r2r_protocol #robot2robot_protocol #ai #aiparivartanresearchlab #techparivartan
https://huggingface.co/blog/rajkumarrawal/rawalraj