12 citations · 15 across the 14 of their papers we have counts for
15 papers
Multiscale Gaussian-Mixture Modeling for HMM Post-Processing in Selective Auditory Attention Decoding
Tianyi Li, Simon Geirnaert, Bert De Smedt +1
Selective auditory attention decoding (sAAD) infers from electroencephalography (EEG) which speaker a listener attends to in multi-speaker scenarios. A widely used approach reconst…
DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
Tianyi Li, Yaxin Luo, Xinyi Shang +1
Speculative decoding losslessly accelerates autoregressive language models by verifying multiple draft tokens in parallel. Diffusion-based drafters further reduce proposal latency…
Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
Tianyi Li, Zhiqiang Shen
Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the inte…
Dataset-Level Metrics Attenuate Non-Determinism: A Fine-Grained Non-Determinism Evaluation in Diffusion Language Models
Zhengyu Fang, Zhimeng Jiang, Huiyuan Chen +5
Diffusion language models (DLMs) have emerged as a promising paradigm for large language models (LLMs), yet the non-deterministic behavior of DLMs remains poorly understood. The ex…
Tracing Prompt-Level Trajectories to Understand Student Learning with AI in Programming Education
Tianyu Shao, Miguel Feijóo-García, Yi Zhang +4
As AI tools such as ChatGPT enter programming classrooms, students encounter differing rules across courses and instructors, which shape how they use AI and leave them with unequal…
Sink-Aware Pruning for Diffusion Language Models
Aidar Myrzakhan, Tianyi Li, Bowei Guo +2
Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited from autoregressi…
MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models
Tianyi Li, Shihui Zang, Moritz Münchmeyer
We develop a general framework to discover scientific algorithms and apply it to three problems in computational cosmology. Our code, MadEvolve, is similar to Google's AlphaEvolve,…
CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
Jiacheng Guo, Suozhi Huang, Zixin Yao +16
This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in t…
Estimating the Error of Large Language Models at Pairwise Text Comparison
Tianyi Li
We measure LLMs' output error at pairwise text comparison, noting the probability of error in their preferences. Our method does not rely on the ground truth and supports two scena…
A Multi-Task Evaluation of LLMs' Processing of Academic Text Input
Tianyi Li, Yu Qin, Olivia R. Liu Sheng
How much large language models (LLMs) can aid scientific discovery, notably in assisting academic peer review, is in heated debate. Between a literature digest and a human-comparab…
A Survey on Diffusion Language Models
Tianyi Li, Mingda Chen, Bowei Guo +1
Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm. By generating tokens in parallel through…
User-Centered Design with AI in the Loop: A Case Study of Rapid User Interface Prototyping with "Vibe Coding"
Tianyi Li, Tanay Maheshwari, Alex Voelker
We present a case study of using generative user interfaces, or ``vibe coding,'' a method leveraging large language models (LLMs) for generating code via natural language prompts,…
Open-Sora: Democratizing Efficient Video Production for All
Zangwei Zheng, Xiangyu Peng, Tianji Yang +6
Vision and language are the two foundational senses for humans, and they build up our cognitive ability and intelligence. While significant breakthroughs have been made in AI langu…
HalluCana: Fixing LLM Hallucination with A Canary Lookahead
Tianyi Li, Erenay Dayanik, Shubhi Tyagi +1
In this paper, we present HalluCana, a canary lookahead to detect and correct factuality hallucinations of Large Language Models (LLMs) in long-form generation. HalluCana detects a…
Dial-insight: Fine-tuning Large Language Models with High-Quality Domain-Specific Data Preventing Capability Collapse
Jianwei Sun, Chaoyang Mei, Linlin Wei +4
The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains. A common challenge when fine-tunin…