The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Paper • 2606.29526 • Published • 163
Борисов Ксения
asher-hill12
AI & ML interests
Open-source multimodal experiment workflows.
Recent Activity
liked a dataset 5 days ago
nvidia/Llama-Nemotron-Post-Training-Dataset liked a dataset 8 days ago
vraiRobotLab/fake_bi_pick_place_leftOrganizations
None yet
upvoted a paper 10 days ago
upvoted a paper 27 days ago
upvoted 5
papers about 2 months ago
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Paper • 2605.28816 • Published • 431
VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild
Paper • 2605.27882 • Published • 16
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation
Paper • 2605.23271 • Published • 81
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models
Paper • 2605.18601 • Published • 6
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
Paper • 2605.12496 • Published • 31
upvoted a paper 2 months ago
upvoted 7
papers 3 months ago
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 245
PlayCoder: Making LLM-Generated GUI Code Playable
Paper • 2604.19742 • Published • 26
Adam's Law: Textual Frequency Law on Large Language Models
Paper • 2604.02176 • Published • 509
AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Paper • 2604.04184 • Published • 52
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 639
An Empirical Recipe for Universal Phone Recognition
Paper • 2603.29042 • Published • 5
SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise
Paper • 2602.12783 • Published • 246