Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis Paper β’ 2601.14253 β’ Published 15 days ago β’ 10
V-DPM: 4D Video Reconstruction with Dynamic Point Maps Paper β’ 2601.09499 β’ Published 21 days ago β’ 9
UM-Text: A Unified Multimodal Model for Image Understanding Paper β’ 2601.08321 β’ Published 22 days ago β’ 9
ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation Paper β’ 2601.03955 β’ Published 28 days ago β’ 3
FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation Paper β’ 2512.24724 β’ Published Dec 31, 2025 β’ 7
Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow Paper β’ 2512.24766 β’ Published Dec 31, 2025 β’ 9
What matters for Representation Alignment: Global Information or Spatial Structure? Paper β’ 2512.10794 β’ Published Dec 11, 2025 β’ 9
ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models Paper β’ 2512.07843 β’ Published Nov 24, 2025 β’ 22
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution Paper β’ 2510.08697 β’ Published Oct 9, 2025 β’ 39
view post Post 4290 These are the current best Generative 3DRender:#1 - CSM#2 - TRELLIS (open-source)#3 - Zaohaowu3DTopology:#1 - Hunyuan3D-2#2 - TRELLIS (open-source)#3 - Hunyuan3D-2.1as voted/submitted openly on https://huggingface.co/spaces/dylanebert/3d-arena See translation 1 reply Β· π 3 3 + Reply
view post Post 2799 https://huggingface.co/spaces/dylanebert/3d-arena now supports topology-only voting and ranking!Let's see which Gen3D model produces the best topology See translation π 3 3 + Reply
view post Post 580 https://huggingface.co/spaces/dylanebert/3d-arena now has an official paper!Check it out 3D Arena: An Open Platform for Generative 3D Evaluation (2506.18787) See translation π€ 1 1 + Reply
3D Arena: An Open Platform for Generative 3D Evaluation Paper β’ 2506.18787 β’ Published Jun 23, 2025 β’ 14
view post Post 2775 It will be very interesting to benchmark how energy-efficient the new Falcon-Edge is: https://huggingface.co/blog/tiiuae/falcon-edgeShould be super efficient on CPU according to the numbers published for BitNet: https://github.com/microsoft/BitNet/blob/main/assets/intel_performance.jpg See translation 1 reply Β· π 6 6 β€οΈ 1 1 + Reply
view post Post 4146 You now have the option to filter 3D Arena to open source models.https://huggingface.co/spaces/dylanebert/3d-arena See translation 1 reply Β· π 11 11 + Reply
view post Post 1718 Impressive new Image-to-3D model from Tencent!Here's how the topology (left) compares to the open source state-of-the-art (right)(using the Simplify option for reduced poly count)Try it out here: tencent/Hunyuan3D-2mv See translation π 3 3 π 3 3 + Reply
view post Post 1459 π’ New #1 in Generative 3DCSM/Cube from Common Sense Machines is now the top ranked image-to-3d modelcheck out the results in https://huggingface.co/spaces/dylanebert/3d-arena See translation π 2 2 + Reply