1 citations · 2 across the 8 of their papers we have counts for
10 papers
SEED: Self-Speculative Decoding via Implicit Encoder-Decoder
Hankun Lin, Patrick Pynadath, Ruqi Zhang
Self-speculative decoding accelerates large language model (LLM) inference by drafting tokens from the target model itself, but faces a sharp tradeoff between the quality and cost…
Simplex Relaxation for Discrete Diffusion
Jinya Sakurai, Patrick Pynadath, Satoshi Hayakawa +4
Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the associated reverse prediction problem…
Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion
Pascal Jutras-Dubé, Patrick Pynadath, Jeremy Lu +2
We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on whose discrete anchors are token embeddings. In forward time, anchors release their ma…
Generative Frontiers: Why Evaluation Matters for Diffusion Language Models
Patrick Pynadath, Jiaxin Shi, Ruqi Zhang
Diffusion language models have seen exciting recent progress, offering far more flexibility in generative trajectories than autoregressive models. This flexibility has motivated a…
Why Any-Order Autoregressive Models Need Two-Stream Attention: A Structural-Semantic Tradeoff
Patrick Pynadath, Ruqi Zhang
Any-order autoregressive models (AO-ARMs) offer a promising path toward efficient masked diffusion by enabling native key-value caching, but competitive performance has so far requ…
CANDI: Hybrid Discrete-Continuous Diffusion Models
Patrick Pynadath, Jiaxin Shi, Ruqi Zhang
While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed pure discrete for…
VERA: Variational Inference Framework for Jailbreaking Large Language Models
Anamika Lochab, Lu Yan, Patrick Pynadath +2
The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings. Without…
Single-Step Consistent Diffusion Samplers
Pascal Jutras-Dubé, Patrick Pynadath, Ruqi Zhang
Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterat…
Controlled LLM Decoding via Discrete Auto-regressive Biasing
Patrick Pynadath, Ruqi Zhang
Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday…
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
Patrick Pynadath, Riddhiman Bhattacharya, Arun Hariharan +1
Discrete distributions, particularly in high-dimensional deep models, are often highly multimodal due to inherent discontinuities. While gradient-based discrete sampling has proven…