OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
Paper • 2609.39903 • Published • 52
AI & ML interests
None defined yet.
Recent Activity
View all activity
iLOVE2D
submitted a
paper to Daily Papers 3 days ago
YhangChen
authored 9
papers 6 days ago
Diffusion-based Cumulative Adversarial Purification for Vision Language Models
Paper • 2506.03933 • Published
Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees
Paper • 2502.12678 • Published
Membership Inference Attacks against Large Vision-Language Models
Paper • 2411.02902 • Published
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
Paper • 2009.11094 • Published
High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
Paper • 2406.03171 • Published
ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement
Paper • 2609.13425 • Published • 9
Order-Preserving GFlowNets
Paper • 2310.00386 • Published
A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
Paper • 2606.11189 • Published • 2
Generalization of Scaled Deep ResNets in the Mean-Field Regime
Paper • 2403.09889 • Published
AmeyaPrabhu
authored 10
papers 22 days ago
Stealing Reasoning Traces from Proprietary LLM APIs
Paper • 2608.09867 • Published • 122
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
Paper • 2606.32034 • Published • 10
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Paper • 2606.28551 • Published • 52
VGGSounder: Audio-Visual Evaluations for Foundation Models
Paper • 2508.08237 • Published • 1
FutureSim: Replaying World Events to Evaluate Adaptive Agents
Paper • 2605.15188 • Published • 7
Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss
Paper • 2604.12911 • Published
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
Paper • 2604.14140 • Published • 1
Personalizing Text-to-Image Generation to Individual Taste
Paper • 2604.07427 • Published • 7
PostTrainBench: Can LLM Agents Automate LLM Post-Training?
Paper • 2603.08640 • Published • 3
Scaling Open-Ended Reasoning to Predict the Future
Paper • 2512.25070 • Published • 20