Cornell University

university

Verified

https://www.cornell.edu

AI & ML interests

None defined yet.

Recent Activity

wwwbxy123 authored a paper about 1 month ago

SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision

wwwbxy123 authored a paper about 1 month ago

Meissa: Multi-modal Medical Agentic Intelligence

nthngdy submitted a paper about 1 month ago

Lost in Backpropagation: The LM Head is a Gradient Bottleneck

View all activity

Papers

Lost in Backpropagation: The LM Head is a Gradient Bottleneck

Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding

View all Papers

authored 2 papers about 1 month ago

SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision

Paper • 2510.02797 • Published Oct 3, 2025

Meissa: Multi-modal Medical Agentic Intelligence

Paper • 2603.09018 • Published Mar 9 • 5

submitted a paper to Daily Papers about 1 month ago

Lost in Backpropagation: The LM Head is a Gradient Bottleneck

Paper • 2603.10145 • Published Mar 10 • 13

submitted a paper to Daily Papers 3 months ago

YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation

Paper • 2602.00168 • Published Jan 29 • 1

authored a paper 4 months ago

Nested Learning: The Illusion of Deep Learning Architectures

Paper • 2512.24695 • Published Dec 31, 2025 • 45

submitted a paper to Daily Papers 4 months ago

Nested Learning: The Illusion of Deep Learning Architectures

Paper • 2512.24695 • Published Dec 31, 2025 • 45

authored 2 papers 4 months ago

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity

Paper • 2406.02913 • Published Jun 5, 2024

SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations

Paper • 2512.14080 • Published Dec 16, 2025 • 9

authored a paper 6 months ago

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Paper • 2403.05530 • Published Mar 8, 2024 • 64

authored 2 papers 8 months ago

ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations

Paper • 2502.10999 • Published Feb 16, 2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Paper • 2507.06261 • Published Jul 7, 2025 • 67

authored 2 papers 12 months ago

Titans: Learning to Memorize at Test Time

Paper • 2501.00663 • Published Dec 31, 2024 • 31

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Paper • 2504.13173 • Published Apr 17, 2025 • 20

authored 2 papers about 1 year ago

Towards LLM Agents for Earth Observation

Paper • 2504.12110 • Published Apr 16, 2025 • 1

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

Paper • 2410.23891 • Published Oct 31, 2024

authored 2 papers about 1 year ago

Multi-Turn Code Generation Through Single-Step Rewards

Paper • 2502.20380 • Published Feb 27, 2025 • 32

Robotouille: An Asynchronous Planning Benchmark for LLM Agents

Paper • 2502.05227 • Published Feb 6, 2025

authored 3 papers over 1 year ago

Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm

Paper • 2409.07226 • Published Sep 11, 2024 • 1

Towards Rationality in Language and Multimodal Agents: A Survey

Paper • 2406.00252 • Published Jun 1, 2024

MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark

Paper • 2409.18216 • Published Sep 26, 2024 • 1