Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models
Paper • 2605.08472 • Published • 4
AI & ML interests
Geospatial AI, GIS, Spatial Data Science, Remote Sensing, Urban Climate, Urban Heat, Climate Adaptation, Urban Planning, Sustainability, Spatial Machine Learning, Geocomputation.
Recent Activity
rrvaswin
submitted a
paper to Daily Papers 2 days ago
sahsaeedi
authored a
paper 18 days ago
sahsaeedi
submitted a
paper to Daily Papers 22 days ago
Divij
authored a
paper 23 days ago
rohan-debayan
updated 5
Spaces about 1 month ago
NYC Taxi Mobility Equity Dashboard (Voilà)
🚖
NYC FHV and Yellow Taxi equity (Voilà + gridstack)
NYC Taxi Mobility Equity Dashboard (Solara)
🗽
NYC FHV and Yellow Taxi equity across neighborhoods
SF Taxi Mobility Equity Dashboard (Solara)
🚕
SF taxi equity dashboard (Solara + Folium)
SF Mobility Equity Dashboard
🚕
Mobility equity dashboard for San Francisco taxis.
README
🌍
rohan-debayan
published a
Space about 1 month ago
Divij
authored 3
papers 8 months ago
Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents
Paper • 2501.13299 • Published
ThinkTuning: Instilling Cognitive Reflections without Distillation
Paper • 2508.07616 • Published • 1
BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software
Paper • 2509.25248 • Published • 3
sahsaeedi
authored 4
papers 9 months ago
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
Paper • 2407.03525 • Published • 3
Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step Optimization
Paper • 2405.16681 • Published • 4
When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
Paper • 2402.10601 • Published • 1
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench
Paper • 2508.20931 • Published • 16
rrvaswin
authored 3
papers 9 months ago
Triple Preference Optimization: Achieving Better Alignment with Less Data in a Single Step Optimization
Paper • 2405.16681 • Published • 4
ToW: Thoughts of Words Improve Reasoning in Large Language Models
Paper • 2410.16235 • Published
Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
Paper • 2407.14790 • Published