Heli Ben-Hamu
@helibenhamu
Followers
652
Following
620
Media
9
Statuses
146
Research Scientist, FAIR @Meta
NYC
Joined October 2018
RT @zdhnarsil: If you work on **generative models** and are looking for a venue to drop your recent fun work, our (third) SPIGM workshop at….
0
1
0
RT @FEijkelboom: Flow Matching (FM) is one of the hottest ideas in generative AI - and it’s everywhere at #ICML2025. But what is it? And w….
0
256
0
RT @brandondamos: Excited to release AlgoTune!! It's a benchmark and coding agent for optimizing the runtime of numerical code. 🚀 https://t….
0
36
0
RT @adityagrover_: Somewhat dissatisfying that the predominant usage of "world model" is restricted to videos. Beyond just photons, a true….
0
8
0
RT @lipmanya: **Transition Matching** is a new iterative generative paradigm using Flow Matching or AR models to transition between generat….
0
19
0
RT @shaulneta: [1/n].New paper alert! 🚀.Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Mat….
0
46
0
RT @guanhorng_liu: Adjoint-based diffusion samplers have simple & scalable objectives w/o impt weight complication. Like many, though, they….
0
39
0
RT @itai_gat: Excited to share our recent work on corrector sampling in language models! A new sampling method that mitigates error accumul….
0
24
0
RT @RickyTQChen: Padding in our non-AR sequence models? Yuck. 🙅. 👉 Instead of unmasking, our new work *Edit Flows* perform iterative refine….
0
79
0
RT @shaulneta: 📣I'll be at the poster session with our follow-up on Discrete Flow Matching. We derive a closed-form solution to the kinetic….
0
8
0
RT @RickyTQChen: We are presenting 3 orals and 1 spotlight at #ICLR2025 on two primary topics:. On generalizing the data-driven flow match….
0
28
0
RT @HannesStaerk: On monday in our reading group we discuss "Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective" http….
0
32
0
RT @lipmanya: Our **Flow Matching Tutorial** from #NeurIPS2024 is now publicly available: .@helibenhamu @RickyTQCh….
0
92
0
RT @yoav_gelberg: 🧠 Can we train models to manipulate NN weights?. Join us at the first Weight Space Learning Workshop @ICLR_conf to explor….
0
18
0
RT @RickyTQChen: Looking for strong candidates for a *postdoc* position with our team at FAIR NYC! . We develop foundational methods for ge….
0
31
0
RT @bose_joey: 📢 Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR20….
0
27
0
RT @mannat_singh: Flow matching can transform one distribution to another. So why do text-to-image models map noise to images instead of di….
0
44
0
RT @brandondamos: 📢 My team at Meta is hiring visiting PhD students from CMU, UW, Berkeley, and NYU! We study core ML, optimization, amorti….
0
42
0
RT @bose_joey: We're presenting FoldFlow-2 right now! Come check it out in West Ballroom poster # 7210 @AlexanderTong7 @Mila_Quebec @mmbron….
0
16
0
