Shira

ShiraKatz

7 1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 18 days ago

WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents

upvoted a paper 18 days ago

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

upvoted a paper 18 days ago

HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents

View all activity

Organizations

None yet

upvoted 3 papers 18 days ago

WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents

Paper • 2609.36887 • Published 25 days ago • 33

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

Paper • 2610.01780 • Published 23 days ago • 289

HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents

Paper • 2610.03574 • Published 22 days ago • 60

upvoted 4 papers 19 days ago

DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation

Paper • 2610.00360 • Published 24 days ago • 7

Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation

Paper • 2610.00348 • Published 25 days ago • 15

Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs

Paper • 2609.32259 • Published 25 days ago • 104

Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts

Paper • 2610.00314 • Published 25 days ago • 104