NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
Paper • 2610.08430 • Published • 20
Shubhashis Roy Dipta PRO
dipta007
P(doom) Rejects the premise
AI & ML interests
Multimodal Understanding, Reasoning, Generation
Recent Activity
updated a collection 2 days ago
PA3 (EMNLP 2026 main) updated a collection 2 days ago
PA3 (EMNLP 2026 main)Organizations
upvoted a paper 1 day ago
updated a
collection 2 days ago
updated a
collection 28 days ago
liked a
Space 28 days ago
updated a
collection 29 days ago
upvoted a paper 29 days ago
add OCR markdown of the PDF corpus as parquet shards
#3 opened 29 days ago
by dipta007
submitted a
paper to Daily Papers about 1 month ago
published a
Space about 1 month ago
updated a
collection about 1 month ago
updated a
Space about 1 month ago
updated a
dataset about 1 month ago
updated a
model about 1 month ago
authored 6
papers about 1 month ago
OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution
Paper • 2609.06490 • Published • 9
Last Translation Benchmark
Paper • 2609.04173 • Published • 46
PA3: Policy-Aware Agent Alignment through Chain-of-Thought
Paper • 2603.14602 • Published • 1
Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms
Paper • 2608.22335 • Published • 1
DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification
Paper • 2605.27858 • Published
Omni-Modal Dissonance Benchmark: Systematically Breaking Modality Consensus to Probe Robustness and Calibrated Abstention
Paper • 2603.27187 • Published