Replacing the importance sampling ratio with a stop-gradient self-anchored ratio for positive advantages yields unclipped, REINFORCE-equivalent gradients that improve exploration without training instability.
Efficient memory management for large language model serving with pagedattention
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
ROSA introduces shared GPU-pool serving, robotics-aware abstractions for multi-model pipelines, and factory-productivity scheduling that improves output by up to 12.06x over dedicated per-robot systems.
LLM agents trained with a task-success reward on self-generated knowledge can spontaneously explore and adapt to new environments without any rewards or instructions at inference, yielding 20% gains on web tasks and allowing a 14B model to beat Gemini-2.5-Flash.
CoRoVA compresses repository context into compact vectors for code LLMs, reducing TTFT 20-38% versus uncompressed RAG with only a small projector module.
A Dirichlet-prior Bayesian estimator for model success probability replaces Pass@k, delivering faster-converging and more stable rankings with credible intervals on math benchmarks.
PaddleOCR-VL-1.5 is a 0.9B VLM achieving 94.5% SOTA accuracy on OmniDocBench v1.5, with added robustness to physical distortions and support for seal recognition plus text spotting.
citing papers explorer
-
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma
Replacing the importance sampling ratio with a stop-gradient self-anchored ratio for positive advantages yields unclipped, REINFORCE-equivalent gradients that improve exploration without training instability.
-
ROSA: A Robotics Foundation Model Serving System for Robot Factories
ROSA introduces shared GPU-pool serving, robotics-aware abstractions for multi-model pipelines, and factory-productivity scheduling that improves output by up to 12.06x over dedicated per-robot systems.
-
Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
LLM agents trained with a task-success reward on self-generated knowledge can spontaneously explore and adapt to new environments without any rewards or instructions at inference, yielding 20% gains on web tasks and allowing a 14B model to beat Gemini-2.5-Flash.
-
CoRoVA: Compressed Representations for Vector-Augmented Code Completion
CoRoVA compresses repository context into compact vectors for code LLMs, reducing TTFT 20-38% versus uncompressed RAG with only a small projector module.
-
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
A Dirichlet-prior Bayesian estimator for model success probability replaces Pass@k, delivering faster-converging and more stable rankings with credible intervals on math benchmarks.
-
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
PaddleOCR-VL-1.5 is a 0.9B VLM achieving 94.5% SOTA accuracy on OmniDocBench v1.5, with added robustness to physical distortions and support for seal recognition plus text spotting.
- TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions
- CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilities