Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents
Paper • 2607.11433 • Published • 27
Ayaka Nishimura
ayakani
·
AI & ML interests
anomaly detection
multi-agent RL
reward hacking
Recent Activity
liked a dataset about 9 hours ago
Dahoas/full-hh-rlhf liked a dataset about 9 hours ago
D21W12/Diffusion-Deep-Reinforcement-Learning liked a dataset about 9 hours ago
DBbun/motoman-up6-cq-lambda-reinforcement-learning_v1.0Organizations
None yet
upvoted 6
papers about 9 hours ago
EasyPPO: Stabilizing the Critic Is Key
Paper • 2609.36802 • Published • 35
HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents
Paper • 2609.38008 • Published • 35
Context Language Models
Paper • 2609.37725 • Published • 30
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
Paper • 2609.37868 • Published • 51
Scaling Properties of Same-Family On-Policy Distillation
Paper • 2609.32722 • Published • 304
upvoted 8
papers 1 day ago
Selecting Diverse SFT Traces Improves Post-RL Generalization
Paper • 2609.33780 • Published • 36
QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents
Paper • 2609.33848 • Published • 41
An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning
Paper • 2609.35505 • Published • 21
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
Paper • 2609.35347 • Published • 176
Diffusion Reward Models
Paper • 2609.33803 • Published • 33
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
Paper • 2609.34327 • Published • 40
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
Paper • 2609.35767 • Published • 47
Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
Paper • 2609.34972 • Published • 30
upvoted 3
papers 2 days ago
SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL
Paper • 2609.29050 • Published • 13
Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy
Paper • 2609.28660 • Published • 13
VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models
Paper • 2609.04355 • Published • 9
upvoted 3
papers 3 days ago
Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates
Paper • 2609.30077 • Published • 6
Training Object Permanence in World Models
Paper • 2609.28654 • Published • 239
RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation
Paper • 2609.29028 • Published • 15