Thomas

tomdot-dev

·

AI & ML interests

None yet

Recent Activity

updated a collection less than a minute ago

updated a collection 4 minutes ago

updated a collection 4 minutes ago

View all activity

Organizations

None yet

upvoted an article 10 minutes ago

Article

ViKernel: Why the Kill Switch Must Live Inside the Model

FINAL-Bench

•

about 22 hours ago

• 11

upvoted an article 15 minutes ago

Article

AtMem routed-v4 on DolphinBench: 479/600, and what the failed actions show

javadtaghia

•

1 day ago

• 1

upvoted an article 18 minutes ago

Article

MirrorSentinel-Elevator: Debugging Multimodal Sensor Data in FiftyOne

harpreetsahota

•

2 days ago

• 1

upvoted a collection 1 day ago

RWKV7-Gxx-GGUF

GGUF of RWKV7-G series reasoning models • 8 items • Updated 1 day ago • 16

upvoted 5 articles 11 days ago

Article

Understanding the Role of Context Management in RL Post-Training

Tavily

•

11 days ago

• 1

Article

Building Deep Research: How we Achieved State of the Art

Tavily

•

Nov 24, 2025

• 38

Article

How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications

Dharma-AI

•

12 days ago

• 37

Article

Patchright + CapSolver: A Tested Main-Context Adapter for CAPTCHA Detection

CapSolverAI

•

11 days ago

• 1

Article

NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required

nvidia

•

12 days ago

• 37

upvoted a collection 19 days ago

Deliberation-Style RecursiveMAS

5 items • Updated Jun 25 • 4

upvoted a collection 20 days ago

🌊 MoM 1.0

long context models for MoM multilingual embeddings • 5 items • Updated Sep 13 • 6

upvoted 2 collections 22 days ago

CYBER-FROST 3.8

Official CYBER-FROST 3.8 releases for authorized cybersecurity research: BF16, FP8, and NVFP4 checkpoints. • 6 items • Updated 27 days ago • 8

Recent medium models

100 items • Updated 1 day ago • 19

upvoted an article 22 days ago

Article

"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"

FINAL-Bench

•

Apr 13

• 16

upvoted a collection 22 days ago

HF Ofiicial Benchs

14 items • Updated 3 days ago • 12

upvoted a collection 25 days ago

Apodex-1.1

5 items • Updated Sep 10 • 59

upvoted a collection about 2 months ago

GSQ

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling, https://huggingface.co/papers/2604.18556 • 8 items • Updated 11 days ago • 17

upvoted a collection 2 months ago

Granite 4.2 Language Models

Efficient reasoning and thinking language models for multilingual generation, coding, and AI assistant workflows. • 27 items • Updated 14 days ago • 51

upvoted a paper 3 months ago

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published Jul 30 • 108

upvoted a collection 3 months ago

NextCoder

NextCoder family of code-editing LMs developed with Selective Knowledge Transfer and its training data. • 6 items • Updated Jul 9, 2025 • 82