5 papers
Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization
Tatsuhiro Nakamori, Laura Gomezjurado Gonzalez, Ganesh Talluri +5
Low-rank gradient compression reduces communication in distributed training by representing updates with rank- factors. Dion is a recent method that approximates Muon, a spectra…
Shielded RecRL: Explanation Generation for Recommender Systems without Ranking Degradation
Ansh Tiwari, Ayush Chauhan
We introduce Shielded RecRL, a reinforcement learning approach to generate personalized explanations for recommender systems without sacrificing the system's original ranking perfo…
Local Timescale Gates for Timescale-Robust Continual Spiking Neural Networks
Ansh Tiwari, Ayush Chauhan
Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory…
Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes
Maximus Powers, Shaina Raza, Alex Chang +5
Representational harms in language technologies often occur in short spans within otherwise neutral text, where phrases may simultaneously convey generalizations, unfairness, or st…
TuneGenie: Reasoning-based LLM agents for preferential music generation
Amitesh Pandey, Jafarbek Arifdjanov, Ansh Tiwari
Recently, Large language models (LLMs) have shown great promise across a diversity of tasks, ranging from generating images to reasoning spatially. Considering their remarkable (an…