Yash Kant
@yash2kant
Followers
905
Following
8K
Media
67
Statuses
1K
ai phd @uoftcompsci // prev @meta @snap @georgiatech
Toronto, Ontario
Joined August 2011
RT @Alibaba_Qwen: 🚀 Meet Qwen-Image — a 20B MMDiT model for next-gen text-to-image generation. Especially strong at creating stunning graph….
0
666
0
RT @LumaLabsAI: Introducing Modify with Instructions in Dream Machine. Use natural language to direct changes across VFX, advertising, film….
0
170
0
RT @Alibaba_Wan: 🚀 Introducing Wan2.2: The World's First Open-Source MoE-Architecture Video Generation Model with Cinematic Control!. 🔥 Key….
0
305
0
RT @cloneofsimo: Very interesting, standard attention causes vanishing gradient due to most prob being very small after some training. LASE….
0
45
0
RT @deviparikh: Some samples of (positive) feedback from Scouts users this past week! . We're continuing to let people in every day. Join t….
0
6
0
RT @msalbergo: Dear @NeurIPSConf -- it seems OpenReview is down entirely, and we cannot submit reviews for the upcoming review deadline ton….
0
10
0
RT @yongyuanxi: Adding horizontal lines to images improves VLM (vision language model) performance of tasks like counting, visual search, s….
0
74
0
RT @MZollhoefer: My research group in the Codec Avatars lab at Meta contributed by developing the technology required to display the output….
0
8
0
RT @realNingYu: 🔊 #ICCV2025 acceptance: ⚡FlashDepth⚡ estimates accurate and consistent depth for 2K-resolution videos in a real-time (24 FP….
0
14
0
RT @eyelinestudios: The latest research paper from @eyelinestudios, FlashDepth, has been accepted to the International Conference on Comput….
0
8
0
RT @mangahomanga: Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a h….
0
45
0
RT @3DVconf: 📢 3DV 2026 – Call for Papers is Out!. 📝 Paper Deadline: Aug 18.🎥 Supplementary: Aug 21.🔗 📅 Conference….
0
16
0
RT @itsyehonathan: One paper accepted to #ICCV2025! . 💡 “LightSwitch: Multi-view Relighting with Material-guided Diffusion” 💡 . Will releas….
0
1
0
RT @FAL: 🚨🎬 MiniMax @Hailuo_AI 's latest video model, Hailuo 02, is now available exclusively on fal's API platform. For just 28 cents per….
0
61
0
RT @mangahomanga: I'm attending @RoboticsSciSys for the first time #RSS2025 in LA. Excited to be giving two invited talks, at the Continual….
0
5
0
RT @soumikRakshit96: ✨ CVPR 2025 highlight #3 ---.MatAnyone: Stable Video Matting with Consistent Memory Propagation. MatAnyone is a robust….
0
22
0
RT @realNingYu: Grateful to everyone who stopped by our oral presentation and posters during the whirlwind of #CVPR2025 — we know you had p….
0
4
0