David Fleet
@fleet_dj
Followers
463
Following
32
Statuses
37
Google Research, Brain Team; and University of Toronto.
Joined November 2016
RT @s_shekarforoush: We compare our method with the state-of-the-art on both synthetic and experimental benchmarks. Empirically, cryoSPIN o…
0
1
0
RT @s_shekarforoush: 🎉🎉Excited to share that “CryoSPIN” has been accepted to #NeurIPS2024! Special thanks to my amazing collaborators and s…
0
29
0
RT @watson_nn: Why use RLHF when u can backprop through the sampler with any differentiable reward🥹🥹🥹
0
2
0
RT @clark_kev: DRaFT backpropagates the reward directly into LoRA parameters – we don’t need to use RL because diffusion sampling is differ…
0
2
0
RT @clark_kev: Our best variant, DRaFT-LV, learns 2x faster than ReFL ( and 100x faster than RL. (3/5) https://t.co…
0
2
0
RT @priyankjaini: .@clark_kev & I are excited to share our new work on studying Imagen by evaluating it as a zero-shot classifier! Highligh…
0
17
0
RT @clark_kev: We can reduce the effect of the fine-tuning or mix different reward functions post-training simply by scaling down or mixing…
0
2
0
RT @structurabio: 📄 An updated paper describing 3D Flexible Refinement is now out in @naturemethods! Paper: It des…
0
22
0
RT @Chitwan_Saharia: Awesome work by Hshmat. The work showcases yet another evidence of how effective noise conditioning augmentation can b…
0
2
0
RT @HshmatSahak: Thrilled to announce SR3+, our new model that establishes a new state-of-the-art on diffusion-based super-resolution for i…
0
13
0
RT @GeorgeEDahl: We've just released the first version of our Deep Learning Tuning Playbook! This is our attempt to distill our process for…
0
827
0
RT @watson_nn: Excited to announce our work on novel view synthesis with diffusion models! Our model can lift a single 2d image into 3d. h…
0
912
0
RT @hojonathanho: Excited to announce Imagen Video, our new text-conditioned video diffusion model that generates 1280x768 24fps HD videos!…
0
716
0
RT @bradneuberg: If you don’t think DallE-2 and Imagen are an Alexnet level moment in the machine learning world you aren’t paying attentio…
0
80
0
RT @Chitwan_Saharia: Daniel has created some of the most amazing #Imagen images so far. Keep an eye out.
0
11
0
RT @mo_norouzi: If you have any kind of feedback for the #imagen team, we'd love to hear it! @Chitwan_Saharia, @wc…
0
3
0
RT @dpkingma: It was 16 years ago, in 2006, that @geoffreyhinton et al released their demo of deep belief nets. Undergrad me was highly imp…
0
258
0
RT @Chitwan_Saharia: @RolandMemisevic @mo_norouzi @wellingmax a blue elephant riding a unicycle on the moon #imagen
0
5
0