Aleksei's picture

22

Aleksei

LeonMeon

LeonMeon

AI & ML interests

CV

Organizations

None yet

upvoted 5 papers 4 months ago

Why Language Models Hallucinate

Paper • 2509.04664 • Published Sep 4, 2025 • 195

Autoregressive Universal Video Segmentation Model

Paper • 2508.19242 • Published Aug 26, 2025 • 28

PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

Paper • 2508.17188 • Published Aug 24, 2025 • 17

VibeVoice Technical Report

Paper • 2508.19205 • Published Aug 26, 2025 • 139

CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics

Paper • 2508.18124 • Published Aug 25, 2025 • 49

upvoted 2 papers 5 months ago

A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence

Paper • 2507.21046 • Published Jul 28, 2025 • 82

AnimalClue: Recognizing Animals by their Traces

Paper • 2507.20240 • Published Jul 27, 2025 • 9

upvoted a paper 6 months ago

MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation

Paper • 2506.23151 • Published Jun 29, 2025 • 24

upvoted 5 papers 7 months ago

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published Jun 7, 2025 • 71

Let's Predict Sentence by Sentence

Paper • 2505.22202 • Published May 28, 2025 • 19

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Paper • 2505.18600 • Published May 24, 2025 • 48

MMaDA: Multimodal Large Diffusion Language Models

Paper • 2505.15809 • Published May 21, 2025 • 97

TabSTAR: A Foundation Tabular Model With Semantically Target-Aware Representations

Paper • 2505.18125 • Published May 23, 2025 • 112

upvoted 5 papers 8 months ago

A Preliminary Study for GPT-4o on Image Restoration

Paper • 2505.05621 • Published May 8, 2025 • 11

Healthy LLMs? Benchmarking LLM Knowledge of UK Government Public Health Information

Paper • 2505.06046 • Published May 9, 2025 • 15

Unified Continuous Generative Models

Paper • 2505.07447 • Published May 12, 2025 • 43

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Paper • 2505.09568 • Published May 14, 2025 • 98

Depth Anything with Any Prior

Paper • 2505.10565 • Published May 15, 2025 • 12

upvoted 2 papers 10 months ago

Scale-wise Distillation of Diffusion Models

Paper • 2503.16397 • Published Mar 20, 2025 • 41

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Paper • 2503.15558 • Published Mar 18, 2025 • 50