Soumava Paul
@__mvp18__
Followers
55
Following
3K
Media
0
Statuses
154
Research Intern @inria_paris • MSc Visual Computing @SIC_Saar and @cvml_mpiinf • Prev @HP, @iiscbangalore, @IBMResearch • @IITKgp EECS alumnus
Paris, France
Joined September 2018
RT @karpathy: How to build a thriving open source community by writing code like bacteria do 🦠. Bacterial code (genomes) are:. - small (eac….
0
1K
0
RT @konstmish: A gentle reminder that TMLR is a great journal that allows you to submit your papers when they are ready rather than rushing….
0
22
0
RT @docmilanfar: A surprising & little-known results in classical statistics:. Mean (μ) and median (m) are within one std deviation:. |μ−m|….
0
197
0
RT @deedydas: A small Chinese startup dropped a video gen model that beats Google's Veo 3 in almost every test you throw at it. Generates….
0
302
0
RT @giffmana: Ladies and gentlemen, i present to you the most surreal exchange I've had on x the everything app:
0
68
0
RT @baophamhq: Diffusion models create novel images, but they can also memorize samples from the training set. How do they blend stored fea….
0
85
0
RT @abhshkdz: We're excited to launch Scouts — always-on AI agents that monitor the web for anything you care about.
0
174
0
RT @ChombaBupe: I looked deeply in the mathematical formulation of diffusion models (image & video generators) & they are inherently doing….
0
142
0
RT @iam_NCJ: What if a Transformer could render?.Not text → image. But mesh → image — with global illumination. No rasterizers. No ray-tra….
0
86
0
RT @HashemGhaili: Prompt Theory (Made with Veo 3). What if AI-generated characters refused to believe they were AI-generated? https://t.co/….
0
4K
0
RT @Google: Say goodbye to the silent era of video generation: Introducing Veo 3 — with native audio generation. 🗣️. Quality is up from Veo….
0
3K
0
RT @_AndrewZhao: if submitting to @NeurIPSConf, DONT forget to add this at the END. Defend against AI reviewers & lost in the middle:. \tex….
0
67
0
RT @j0nathanj: Introducing Multiverse: the first AI-generated multiplayer game. Multiplayer was the missing piece in AI-generated worlds —….
0
198
0
RT @keenanisalive: Here's a nice "proof without words":. The sum of the squares of several positive values can never be bigger than the squ….
0
580
0
RT @hila_chefer: VideoJAM is our new framework for improved motion generation from @AIatMeta. We show that video generators struggle with m….
0
197
0
RT @rtk254: Video models != world models . "We find that across a range of current models (Sora, Runway, Pika, Lumiere, Stable Video Diffus….
0
126
0