SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization Paper โข 2602.04811 โข Published 18 days ago โข 2
Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis Paper โข 2601.14253 โข Published Jan 20 โข 10
V-DPM: 4D Video Reconstruction with Dynamic Point Maps Paper โข 2601.09499 โข Published Jan 14 โข 9
UM-Text: A Unified Multimodal Model for Image Understanding Paper โข 2601.08321 โข Published Jan 13 โข 10
ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation Paper โข 2601.03955 โข Published Jan 7 โข 3
FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation Paper โข 2512.24724 โข Published Dec 31, 2025 โข 7
Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow Paper โข 2512.24766 โข Published Dec 31, 2025 โข 9
FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos Paper โข 2512.10927 โข Published Dec 11, 2025 โข 6
What matters for Representation Alignment: Global Information or Spatial Structure? Paper โข 2512.10794 โข Published Dec 11, 2025 โข 9
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models Paper โข 2512.07843 โข Published Nov 24, 2025 โข 22
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution Paper โข 2510.08697 โข Published Oct 9, 2025 โข 39
Describe Anything: Detailed Localized Image and Video Captioning Paper โข 2504.16072 โข Published Apr 22, 2025 โข 64
PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding Paper โข 2501.16411 โข Published Jan 27, 2025 โข 19
view post Post 51629 Google drops Gemini 2.0 Flash Thinkinga new experimental model that unlocks stronger reasoning capabilities and shows its thoughts. The model plans (with thoughts visible), can solve complex problems with Flash speeds, and morenow available in anychat, try it out: https://huggingface.co/spaces/akhaliq/anychat See translation 5 replies ยท ๐ 12 12 ๐ฅ 6 6 ๐ 4 4 ๐ 2 2 + Reply
view post Post 50655 QwQ-32B-Preview is now available in anychatA reasoning model that is competitive with OpenAI o1-mini and o1-previewtry it out: https://huggingface.co/spaces/akhaliq/anychat See translation 2 replies ยท โค๏ธ 3 3 ๐ 2 2 + Reply
view post Post 5094 New model drop in anychatallenai/Llama-3.1-Tulu-3-8B is now availabletry it here: https://huggingface.co/spaces/akhaliq/anychat See translation ๐ฅ 3 3 ๐ 1 1 + Reply
view post Post 3844 anychatsupports chatgpt, gemini, perplexity, claude, meta llama, grok all in one apptry it out there: https://huggingface.co/spaces/akhaliq/anychat โค๏ธ 7 7 ๐ 4 4 ๐ฅ 2 2 + Reply