OctoT2I uses a no-supervision PSEL loop to discover model capability frontiers and route T2I tasks, reaching 0.96 GenEval score with 90.3% speedup over Flow-GRPO.
Multi-agent image restoration
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
SEAR introduces a dual-process agentic framework for image restoration that combines pruning-aware MCTS planning with self-evolving episodic memory to address greedy search and episodic amnesia limitations.
HDRAgent is the first agent-driven framework for multi-exposure HDR imaging that uses MLLM scene perception, contextual knowledge matching, and perception-distortion feedback to reduce ghosting artifacts.
DiTTo reduces optimal restoration trajectory dataset construction from quadratic to linear cost via a simulator and adds order-aware alignment for plug-and-play extensibility to new experts, claiming SOTA quality on multi-degradation benchmarks.
An RL-trained lightweight agent uses MLLM perceptual rewards to perform efficient label-free image restoration, matching SOTA on full-reference metrics and surpassing prior work on no-reference metrics.
EvoIR-Agent introduces a hierarchical experience pool and self-evolving mechanism to improve training-free image restoration agents, claiming significant metric leads and better performance-efficiency balance.
OPERA jointly optimizes restoration planning via RL over tool compositions and execution via agent-guided co-training of tools, claiming consistent gains over all-in-one models and prior agent methods on multi-degradation benchmarks.