261 citations · 359 across the 25 of their papers we have counts for
7 papers · 1 filter
Aliasing-Free Neural Audio Synthesis
Yicheng Gu, Junan Zhang, Chaoren Wang +3
In neural audio synthesis, neural vocoders and codecs are models that reconstruct waveforms from acoustic and latent representations, which are essential to the resulting audio qua…
Optimal Inference Schedules for Masked Diffusion Models
Sitan Chen, Kevin Cong, Jerry Li
A major bottleneck of standard auto-regressive large language models is that their inference process is inherently sequential, resulting in very long and costly inference times. To…
Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization
Tiancheng Xing, Jerry Li, Yixuan Du +1
Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose th…
Robust Estimation Under Heterogeneous Corruption Rates
Syomantak Chaudhuri, Jerry Li, Thomas A. Courtade
We study the problem of robust estimation under heterogeneous corruption rates, where each sample may be independently corrupted with a known but non-identical probability. This se…
Beyond ROUGE: N-Gram Subspace Features for LLM Hallucination Detection
Jerry Li, Evangelos Papalexakis
Large Language Models (LLMs) have demonstrated effectiveness across a wide variety of tasks involving natural language, however, a fundamental problem of hallucinations still plagu…
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
Scott Geng, Hamish Ivison, Chun-Liang Li +4
Improvements in language models are often driven by improving the quality of the data we train them on, which can be limiting when strong supervision is scarce. In this work, we sh…
S4S: Solving for a Diffusion Model Solver
Eric Frankel, Sitan Chen, Jerry Li +3
Diffusion models (DMs) create samples from a data distribution by starting from random noise and iteratively solving a reverse-time ordinary differential equation (ODE). Because ea…