Papers arxiv:2605.13027 PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution Published on May 13 Submitted by 张扬 on May 15 Authors: , , , , Abstract PRISM is a diffusion-based text super-resolution framework that improves accuracy under… …
… In this paper, we propose an exploration-aware reinforcement learning framework that enables LLM agents to adaptively explore only when uncertainty is high. …
… A natural next step is to let the actor dynamically route among these temporal heads, using either differentiable attention or heuristic uncertainty weights . …
… Despite recent advances, several key challenges remain, including 1 online inference with robust uncertainty updates over multiple hypotheses; 2 efficient reasoning suitable for real-time assistance; and 3 the lack of ground-truth mental state annotations in real-world domains. …
… Through careful ablations, we show how FutureSim offers a realistic setting to study emerging re search directions like long-horizon test-time adaptation , search , memory , and reasoning about uncertainty . …
… The following papers were recommended by the Semantic Scholar API Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling 2026 Learning When to Attend: Conditional Memory Access for Long-Context LLMs 2026 OASIS: Online Activation Subspace Learning for Memo… …
… The following papers were recommended by the Semantic Scholar API DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning 2026 Learning to Route Electric Trucks Under Operational Uncertainty 2026 Two-Stage Learned Decomposition for Scalable Routing on Multigraphs 20… …
… The following papers were recommended by the Semantic Scholar API The Detection-Extraction Gap: Models Know the Answer Before They Can Say It 2026 Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces 2026 GCoT-Decoding: Unlocking Deep Reasoning Paths for Univers… …
… We introduce Side-by-Side SxS Interleaved Reasoning , which makes disclosure timing a controllable decision within standard autoregressive generation. …
… The following papers were recommended by the Semantic Scholar API Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model 2026 MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability… …