SenseNova-U1.5: Towards Native Unified Visual Intelligence
Paper • 2609.11929 • Published • 268
Karthik Iyer
kiyer97
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
upvoted a paper about 19 hours ago
SenseNova-U1.5: Towards Native Unified Visual Intelligence upvoted a paper about 19 hours ago
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement liked a dataset 1 day ago
jojo0217/korean_rlhf_datasetOrganizations
None yet
upvoted 2
papers about 19 hours ago
upvoted 5
papers 1 day ago
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
Paper • 2609.13680 • Published • 9
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Paper • 2609.16816 • Published • 7
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Paper • 2609.17523 • Published • 26
StepAudio 3 Music Technical Report
Paper • 2609.16034 • Published • 98
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Paper • 2609.06986 • Published • 341
upvoted 4
papers 2 days ago
MInTRL: Off-policy Intervention can boost On-policy RL
Paper • 2609.12419 • Published • 11
HazardAuditor: From Executable Threats to Safer Computer-Use Agents
Paper • 2609.15134 • Published • 16
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 231
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Paper • 2609.13356 • Published • 252