Mickey Finkelson

AI Researcher @ LTX

🌐

[Mickey Finkelson @mikikiFin]

1/7
New paper 🧵 ScenA generates a multi-speaker audio scene: overlapping speech, laughter, real room noise, from a text description and a few reference voices.

When trained in the obvious way, it ignores the text and decides who speaks on its own. We found out why and fixed it.

[apolinario (poli) @multimodalart]

I think this model is criminally under-hyped

A TTS model that can generate not only 2 speaker audio in one pass, but also scene sound effects; fine-tuned from the LTX audio generation module

https://t.co/i1AbBSFAFn

[Wildminder @wildmindai]

SCENA by Lightricks.
Reference-driven multi-speaker audio scene gen!
Prompt "two friends arguing in a rainy cafe" + two ref voice clips -> full 20s audio scene in one pass.
Overlapping speech, room echo, background sounds - all baked in.
- based on LTX-2.3
- beats ZipVoice-Dialog/MOSS-TTSD
- up to 3 ref speakers
- perfect text alignment
-Identity-aware positional encodings
- SOTA performance

https://t.co/69UCtDTzzO

[Mickey Finkelson @mikikiFin]

🔊 Audio on for this one!

Code + checkpoint for ScenA, our multi-speaker audio scene generation model, are out!

Reference voices + a prompt → a full conversational scene, prompt alone decides who speaks where.

https://t.co/HeVuoPh0Zw
https://t.co/wvLA5K848s

[Mickey Finkelson @mikikiFin]

Awesome work for consistent video editing! Comes with a recommended promotion video

[Sagi Polaczek 🦜 @PolaczekSagi]

🎬🎨 LTX-2.3-Sync-LoRA, dataset and weights are out!

check it out yourself :)
https://t.co/ZBvfwF2iPt

[Rishubh Parihar @RishubhParihar]

🌟🚀 Excited to share our latest work: "Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping"!

TL;DR: Stop wasting compute on redundant tokens! We introduce SparseContext that drops reference tokens for speeding up reference-based image generation⚡

[Sara Dorfman @Sara__Dorfman]

Generating images with AI is fun 🤓
Finding the image? Not so much…

The first result is rarely the one. Or the second. Or the third. 🥵

So we built a way to generate diverse possibilities along meaningful semantic axes 🧭 and organize them into a gallery you can effortlessly browse 🧚🏻

Introducing our #ECCV2026 paper: Semantic Browsing: Controllable Diversity for Image Generation ✨

1/5

[Mickey Finkelson @mikikiFin]

📄 https://t.co/zJphk5gS1U
🌐 Samples + code (soon): https://t.co/TyRvYcm2n0
Thanks @OPatashnik & @yoavhacohen and the team at @ltx_io!
Happy to take questions! 🙋‍♂️🙋‍♂️🙋‍♂️

[Mickey Finkelson @mikikiFin]

1/7
New paper 🧵 ScenA generates a multi-speaker audio scene: overlapping speech, laughter, real room noise, from a text description and a few reference voices.

When trained in the obvious way, it ignores the text and decides who speaks on its own. We found out why and fixed it.

[Mickey Finkelson @mikikiFin]

7/7
We don't think the Reference Shortcut is specific to audio. It should hit any reference-conditioned flow-matching model trained with a logit-normal schedule, subject-driven image and video generation included. The lever is the timestep distribution.

[Gal Metzer @galmetz]

Excited to share our work accepted to #SIGGRAPH2026 ! Video generation models struggle with something few talk about: their transformations don't evolve smoothly. You get long boring stretches... then a sudden semantic jump where everything "catches up" at once.

[Shelly Golan @Shelly_Golan1]

1/7

When rewards conflict, what should RL post-training of diffusion models optimize?

In visual generation, objectives are often in tension:
Prompt adherence can conflict with source preservation.
Photorealism can conflict with stylization.

In our new paper, ParetoSlider, we introduce a multi-objective RL framework that trains a single diffusion model for continuous control over competing reward objectives 🧵