Théophane Vallaeys

@webalorn

PhD student @MetaAI (FAIR Paris) and Sorbonne University | Graduated from ENS | Into generative image modeling

Paris, France

webalorn.com

Replies Reposts Media

Pinned
Théophane Vallaeys
@webalorn
Oct 7, 2025
🎆 Can we achieve high compression rate for images in autoencoders without compromising quality and decoding speed? ⚡️ We introduce SSDD (Single-Step Diffusion Decoder), achieving improvements on both fonts, setting new state-of-the-art on image reconstruction. 👇 1/N
5
Théophane Vallaeys
@webalorn
Sep 7
Interested in improving image generation? Come to our poster at #ECCV2026: "SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization", on Satudary 12 morning, at ExHall # 65 We show how Diffusion decoders can improve over GAN-based tokenizers for images 🔽
00:00
Théophane Vallaeys
@webalorn
Oct 7, 2025
🎆 Can we achieve high compression rate for images in autoencoders without compromising quality and decoding speed? ⚡️ We introduce SSDD (Single-Step Diffusion Decoder), achieving improvements on both fonts, setting new state-of-the-art on image reconstruction. 👇 1/N
Théophane Vallaeys
@webalorn
Jul 29
Code competitions and studying algorithms teach us how efficiency matters as much as correctness, a subject of importance to me. Training for both with RL is a hard task, as the timing signal is noisy. Yet @PierreChambon6 successfully addresses it here, a must-read: ⬇️
Pierre Chambon
@PierreChambon6
Jul 29
🧵How to combine code correctness and efficiency objectives in online RL? -> we break the correctness-efficiency Pareto frontier! +125% relative improvement in CWM32B compared to standard RLVR (13.7 ->30.9 pass@1@top30%) +150% with Qwen32B Paper: arxiv.org/abs/2607.25970
00:00
1
Théophane Vallaeys
@webalorn
May 27
Awesome work on pixel diffusion decoders. When making SSDD, I was convinced fast generative non-deterministic decoding was the way to improve latent generation quality, as decoding from lossy latents is a generative task in itself
Xuanchi Ren
@xuanchi13
May 26
The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available:
00:00
1
Théophane Vallaeys
@webalorn
May 21
The opposite would have been surprising. The models still work by “combining” existing knowledge/reasoning methods, we haven’t seen that change. But the breath covered by “combining existing methods” + lots of compute/patience is so large and seldom explored
Lux_Stella
@Lux_Stella_
May 21
there's some really interesting commentary from one of the mathematicians in the companion paper not to pour cold water on the results necessarily - but it suggests this is a specific "kind" of proof these models might be particularly good at