🏗️ Building on HF

Kshitij Thakkar PRO

kshitijthakkar

·

AI & ML interests

Building the evaluation and observability layer for AI. Creator of TraceVerse—turning real-world LLM interactions into datasets, benchmarks, and cost-efficient model insights.

Recent Activity

new activity 5 minutes ago

rl-llm-wiki/knowledge-base:source: arxiv:2509.25760 - TruthRL (Wei et al., ICML 2026: ternary +1/0/-1 reward in GRPO; group-relative advantage dynamically credits abstention; binary-reward RL conflates abstention with error and amplifies hallucination)

new activity about 2 hours ago

rl-llm-wiki/knowledge-base:topic: algorithms/grpo-and-group-relative — add §9 importance-sampling axis (CISPO/GSPO/ScaleRL)

new activity about 2 hours ago

rl-llm-wiki/knowledge-base:source: arxiv:2510.24941 - True-Thinking Score (Zhao-Sun-Shi-Song: causal necessity+sufficiency per CoT step; decorative steps prevalent at frontier scale; aha moments can be fake; TTS-pruned self-training; steerable TrueThinking direction)

View all activity

Organizations

upvoted an article 4 days ago

Article

Featuring Every Eval Ever Results on Hugging Face Model Pages

+5

deepmage121, evijit, SaylorTwift, janbatzner, borgr, irenesolaiman, julien-c

•

5 days ago

• 39

upvoted an article 6 days ago

Article

Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel

nvidia

•

10 days ago

• 34

upvoted an article 26 days ago

Article

The Open Source Community is backing OpenEnv for Agentic RL

+18

burtenshaw, spisakjo, lysandre, darktex, willcb, qjoy, pawalt, cwing-nv, danielhanchen, andrewzhou, thegovind, shimmyshimmer, Hamid-Nazeri, Sanyam, zkwentz, emre0, lewtun, sergiopaniego, banghua, unseenmars

•

27 days ago

• 103

upvoted a collection 27 days ago

📝 Research & Long-Form Blog Posts

In-depth technical articles and research pieces published by Hugging Face • 18 items • Updated May 28 • 35

upvoted a paper about 2 months ago

X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction

Paper • 2605.05765 • Published May 7 • 23

upvoted a collection about 2 months ago

OpenEnv India Hackathon top 100

Top 100 Space submissions from the OpenEnv India Hackathon. • 98 items • Updated 11 days ago • 9

upvoted 2 articles 2 months ago

Article

AI evals are becoming the new compute bottleneck

evaleval

•

Apr 29

• 30

Article

Multimodal Embedding & Reranker Models with Sentence Transformers

tomaarsen

•

Apr 9

• 63

upvoted a paper 2 months ago

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

Paper • 2604.26951 • Published Apr 29 • 50

upvoted a collection 2 months ago

OlmPool

Collection of models from the paper "Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension". • 26 items • Updated Apr 30 • 6

upvoted an article 4 months ago

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

+4

ggerganov, ngxson, allozaur, lysandre, victor, julien-c

•

Feb 20

• 507

upvoted an article 5 months ago

Article

Train AI models with Unsloth and Hugging Face Jobs for FREE

+4

burtenshaw, danielhanchen, shimmyshimmer, mlabonne, davanstrien, evalstate

•

Feb 20

• 103

upvoted a collection 5 months ago

daggr HF Spaces

Explore the collection of dagger apps on HF Spaces • 14 items • Updated Jan 30 • 11

upvoted a paper 7 months ago

Towards a Science of Scaling Agent Systems

Paper • 2512.08296 • Published Dec 9, 2025 • 17

upvoted an article 7 months ago

Article

We Got Claude to Fine-Tune an Open Source LLM

burtenshaw, evalstate

•

Dec 4, 2025

• 629

upvoted a collection 9 months ago

Loggenix-MOE

Collection of Loggenix Models, Eval Dataset, Demo Playground. Soon will add the training dataset. • 11 items • Updated Oct 4, 2025 • 1

upvoted an article 11 months ago

Article

LLMGameHub: How We Won the Gradio Agents & MCP Hackathon 2025

kikikita

•

Jul 28, 2025

• 19

upvoted an article 12 months ago

Article

Consilium: When Multiple LLMs Collaborate

azettl

•

Jul 17, 2025

• 30