Alexey Dontsov

therem's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 1 month ago

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

Paper • 2512.00590 • Published Nov 29, 2025 • 45

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19, 2025 • 227

upvoted a paper about 2 months ago

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization

Paper • 2510.25616 • Published Oct 29, 2025 • 95

upvoted 2 papers 2 months ago

GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver

Paper • 2510.17699 • Published Oct 20, 2025 • 24

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Paper • 2510.11288 • Published Oct 13, 2025 • 48

upvoted a paper 3 months ago

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Paper • 2510.04849 • Published Oct 6, 2025 • 114

authored a paper 3 months ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 18

upvoted a paper 3 months ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 18

commented a paper 3 months ago

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Paper • 2509.22033 • Published Sep 26, 2025 • 18 •

2

authored a paper 3 months ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 27

upvoted a paper 3 months ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 27

commented 2 papers 3 months ago

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Paper • 2509.22067 • Published Sep 26, 2025 • 27 •

2

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol

Paper • 2510.01260 • Published Sep 25, 2025 • 2 •

2

updated a dataset 3 months ago

therem/all_math_generations

Viewer • Updated Oct 2, 2025 • 52.1k • 4

published 2 datasets 3 months ago

therem/all_math_generations

Viewer • Updated Oct 2, 2025 • 52.1k • 4

therem/deepseek_ai_deepseek_math_7b_instructHuggingFaceH4_MATH_500

Updated Sep 22, 2025 • 3

updated a dataset 4 months ago

therem/qwen3_math_ai_minervamath_4x

Viewer • Updated Sep 17, 2025 • 1.09k • 4

published a dataset 4 months ago

therem/qwen3_math_ai_minervamath_4x

Viewer • Updated Sep 17, 2025 • 1.09k • 4

updated a dataset 4 months ago

therem/qwen3_math_ai_olympiadbench_4x

Viewer • Updated Sep 17, 2025 • 2.7k • 3

published a dataset 4 months ago

therem/qwen3_math_ai_olympiadbench_4x

Viewer • Updated Sep 17, 2025 • 2.7k • 3