Patrick Pynadath Profile
Patrick Pynadath

@PatrickPyn35903

Followers
72
Following
92
Media
5
Statuses
32

Phd Student @purdue cs. working on making continuous gradients discrete

Joined October 2024
Don't wanna be here? Send us removal request.
@PatrickPyn35903
Patrick Pynadath
14 days
Continuous diffusion dominates images but fails on discrete data—despite learning continuous gradients that should enable coordinated updates. "CANDI: Hybrid Discrete-Continuous Diffusion Models" explains why and how why hybrid diffusion fixes it! (1/8)
4
12
61
@chenxiao_yang_
Chenxiao Yang
8 days
How powerful are Diffusion LLMs? Can they solve problems that Auto-Regressive (AR) LLMs can’t solve? Check our new paper "On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond" 🔗 https://t.co/aiGTbXMWFE In this work, we show while Diffusion LLMs are indeed more
16
77
372
@FEijkelboom
Floor Eijkelboom
27 days
We asked the same question: how can we combine the strengths of continuous and discrete approaches? Similar to CDCD, in our work, Purrception, we extend Variational FM to model VQ latents through continuous-discrete transport for image generation :D 👉 https://t.co/KIog9mLNWb
@sedielem
Sander Dieleman
1 month
In diffusion LMs, discrete methods have all but displaced continuous ones (🥲). Interesting new trend: why not both? Use continuous methods to make discrete diffusion better. Diffusion duality: https://t.co/KPO56vDygp CADD: https://t.co/CNOIWcUIMo CCDD:
1
13
70
@FEijkelboom
Floor Eijkelboom
8 days
Amazing work by Olga ❤️ We extended Variational FM to Manifold domains for Protein and Material Design, and show how standard Riemannian FM connects to this variational counterpart. Special thanks to all great collaborators on this project. 🐳
@olgazaghen
Olga Zaghen
8 days
Cool news: our extended Riemannian Gaussian VFM paper is out! 🔮 We define and study a variational objective for probability flows 🌀 on manifolds with closed-form geodesics. @FEijkelboom @a_ppln @CongLiu202212 @wellingmax @jwvdm @erikjbekkers 🔥 📜 https://t.co/PE6I6YcoTn
1
6
42
@ssahoo_
Subham Sahoo
12 days
Overwhelmed by the number of Diffusion LLM papers? 🌊 Same here 😭 So I’m starting a Discrete Diffusion Reading Group (@diffusion_llms) with my favorite disciples @jdeschena and @zhihanyang_ ✨ We’ll cover everything—from theory to empirics, from language to molecules. Join
20
41
319
@PatrickPyn35903
Patrick Pynadath
12 days
Awesome work by lab mate! if you are at EMNLP, make sure to check this out!
@lblaoke
Bolian Li
18 days
Can we accelerate test-time alignment? YES! 📃paper: Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner 🔗arXiv: https://t.co/hzDG2l9KZG 📌EMNLP 2025
0
0
2
@JCJesseLai
Chieh-Hsin (Jesse) Lai
14 days
Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on! 📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon. It traces the core
43
438
2K
@sedielem
Sander Dieleman
13 days
The rehabilitation of continuous diffusion for discrete data continues! Check out CANDI by @PatrickPyn35903 @thjashin @ruqi_zhang Their insightful analysis explains why continuous methods have fallen behind, and why self-conditioning is so important. https://t.co/Bqn8Zd7hRz
@sedielem
Sander Dieleman
1 month
In diffusion LMs, discrete methods have all but displaced continuous ones (🥲). Interesting new trend: why not both? Use continuous methods to make discrete diffusion better. Diffusion duality: https://t.co/KPO56vDygp CADD: https://t.co/CNOIWcUIMo CCDD:
3
22
144
@PatrickPyn35903
Patrick Pynadath
14 days
Continuous diffusion dominates images but fails on discrete data—despite learning continuous gradients that should enable coordinated updates. "CANDI: Hybrid Discrete-Continuous Diffusion Models" explains why and how why hybrid diffusion fixes it! (1/8)
4
12
61
@PatrickPyn35903
Patrick Pynadath
14 days
Shoutout to concurrent work CADD ( https://t.co/YZQbJnuW46) and CCDD ( https://t.co/2BDlFsyWmB) exploring hybrid diffusion! Our angle: we explain why continuous diffusion fails on discrete spaces and why hybrid methods work—providing theoretical grounding for this direction (8/8)
Tweet card summary image
arxiv.org
Diffusion language models, especially masked discrete diffusion models, have achieved great success recently. While there are some theoretical and primary empirical results showing the advantages...
0
0
4
@PatrickPyn35903
Patrick Pynadath
14 days
Benefits of continuous diffusion for discrete spaces: 1. Coordinated updates across positions—crucial at low NFE when many tokens update simultaneously 2. Trivial classifier guidance—just compute gradients from off-the-shelf classifiers and add to inference! (6/8)
1
0
2
@PatrickPyn35903
Patrick Pynadath
14 days
Token identifiability predicts: Continuous diffusion: works on small vocabs, fails on large CANDI: effective regardless of vocab size We test on text8 vs. OWT with identical architectures. All three predictions confirmed—theory matches practice! (5/8)
1
0
2
@PatrickPyn35903
Patrick Pynadath
14 days
Simple solution: decouple discrete corruption from noise level and coordinate both explicitly. CANDI's hybrid kernel draws from masked + continuous diffusion, letting models learn discrete conditional structure AND continuous score functions. Best of both worlds! (4/8)
1
0
2
@PatrickPyn35903
Patrick Pynadath
14 days
Key finding: discrete corruption scales exponentially with |V|, but continuous degradation is independent of |V|. This creates "temporal dissonance": when the model learns conditional structure, it can't learn the score function, and vice versa. (3/8)
1
0
2
@PatrickPyn35903
Patrick Pynadath
14 days
Token identifiability reveals two corruption mechanisms: Discrete Identity Corruption: is the wrong token closest? Continuous Rank Degradation: how many wrong tokens are closer? The first enables learning dependencies; the second, the score function. (2/9)
1
0
3
@TaiwoAdebiyi1
Taiwo Adebiyi
7 months
#ICLR2025 wrapped up on a high note. From insightful exchanges on LLMs, probabilistic inference, and optimization at the workshops to reconnecting with @PatrickPyn35903 from @PurdueCS. Grateful to my advisor @ZHANG_Ruda for the chance to be part of such a meaningful event.
0
5
18
@PatrickPyn35903
Patrick Pynadath
7 months
Excited to present this at today’s Poster session! Quick update: poster number is 592. Whova event seems to be outdated, but ICLR website has correct info. Check out the project page if you want to read more! Link: https://t.co/Qc8nRMllxP Time: 10am-12pm, poster number 592
@ruqi_zhang
Ruqi Zhang
7 months
DAB is a controlled decoding algorithm using gradient-based discrete sampling. It achieves better fluency and constraint satisfaction—all with much less computational cost.
0
2
6
@ruqi_zhang
Ruqi Zhang
7 months
DAB is a controlled decoding algorithm using gradient-based discrete sampling. It achieves better fluency and constraint satisfaction—all with much less computational cost.
1
1
1
@ruqi_zhang
Ruqi Zhang
7 months
I won’t be attending #ICLR2025 this year, but my amazing students will be presenting several exciting works: 1️⃣ Inference-time safety in VLMs 2️⃣ Controlled decoding via discrete sampling 3️⃣ Gradient genetic algorithms for drug discovery 4️⃣ Single-step diffusion samplers Catch
1
4
32