arxiv:2608.19741
Tuhin Kundu
tuhink
·
AI & ML interests
Vision, language, machine learning systems
Recent Activity
liked a dataset about 14 hours ago
microsoft/ThinkingBox-Bench authored a paper about 15 hours ago
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models authored a paper about 15 hours ago
One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business WorkflowsOrganizations
models 8
tuhink/hacking-rewards-sft-llama
Text Generation • 3B • Updated • 3
tuhink/hacking-rewards-general-train
Text Classification • 0.4B • Updated • 6
tuhink/hacking-rewards-coherence-train
Text Classification • 0.4B • Updated • 7
tuhink/hacking-rewards-harmless-train
Text Classification • 0.4B • Updated • 6
tuhink/hacking-rewards-math-train
Text Classification • 0.4B • Updated • 10
tuhink/hacking-rewards-code-train
Text Classification • 0.4B • Updated • 4
tuhink/hacking-rewards-helpful-train
Text Classification • 0.4B • Updated • 7
tuhink/hacking-rewards
Updated