Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models

We propose an unsupervised adaptation framework, Self-TAught Recognizer (STAR), which leverages unlabeled data to enhance the robustness of automatic speech recognition (ASR) systems in diverse target domains, such as noise and accents. STAR is developed for prevalent speech foundation models based on Transformer-related architecture with auto-regressive decoding (e.g., Whisper, Canary).

Learning to Move Like Professional Counter-Strike Players

In multiplayer, first-person shooter games like Counter-Strike: Global Offensive (CS:GO), coordinated movement is a critical component of high-level strategic play. However, the complexity of team coordination and the variety of conditions present in popular game maps make it impractical to author hand-crafted movement policies for every scenario. We show that it is possible to take a data-driven approach to creating human-like movement controllers for CS:GO.

SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation

SkillGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment

Guan-Ting (Danny) Liu

Guan-Ting (Danny) Liu completed his Ph.D. in the Graduate Institute of Networking and Multimedia at National Taiwan University in Taipei, Taiwan. During his Ph.D. program, he is advised by Pu-Jen Cheng, Iris Hui-Ru Jiang, and Shao-Hua Sun.

Prithvijit Chattopadhyay

I am a Research Scientist in Deep Imagination Research. I earned my Ph.D. in Computer Science in August 2024 at Georgia Tech, where I was advised by Prof. Judy Hoffman. During my Ph.D., I broadly worked on distribution shift problems in computer vision. My doctoral thesis (see here) was focused on utilizing synthetic data to train robust and reliable vision models.

Avnish Narayan

Yejin Choi

Yejin Choi is a distinguished scientist of Language and Cognition Research at NVIDIA. Her current research focuses on large language models, large reasoning models, and alternative architectures. She is a MacArthur Fellow (class of 2022), named among Time100 Most Influential People in AI in 2023, and a co-recipient of 2 Test-of-Time awards (ACL 2021 and CVPR 2021) and 8 Best and Outstanding Paper Awards at ACL, EMNLP, NAACL, ICML, NeurIPS, and AAAI.

LLM Pruning and Distillation in Practice: The Minitron Approach

VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool

Due to the growing complexity of modern Integrated Circuits (ICs), automating hardware design can prevent a significant amount of human error from the engineering process and result in less errors. Verilog is a popular hardware description language for designing and modeling digital systems; thus, Verilog generation is one of the emerging areas of research to facilitate the design process.

Subscribe to