arXiv:2610. 39439v1 Announce Type: new Abstract: Label-free test-time reinforcement learning adapts vision--language models using rewards derived from their own predictions.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper introduces TTIQ, a test‑time reinforcement learning framework that improves vision‑language model (VLM) adaptation by explicitly measuring image‑question dependence. By teacher‑forcing responses on the original and ablated image‑question pairs, TTIQ derives token‑level likelihood changes to estimate how much each input contributes, then uses these signals to construct a reward that favors jointly grounded, confident responses. Experiments on eight VQA datasets and various VLM sizes show that TTIQ consistently outperforms prior consensus‑based methods and generalizes across model families and unseen datasets.
arXiv:2609.36893v1 Announce Type: new Abstract: Detailed image captioning requires accurate and comprehensive descriptions of fine-grained visual content, yet caption quality spans factual accuracy,...
arXiv:2606. 02578v1 Announce Type: cross Abstract: Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answers.
The paper introduces a test‑time reinforcement learning framework for anomalous video understanding, addressing challenges such as unreliable pseudo‑labels, inadequate reward design, and collapsed group‑relative advantages. It proposes dual‑query consistency filtering, an entropy‑aware consensus reward, and a virtual negative anchor mechanism to improve sample reliability, reward quality, and policy‑gradient signals. Experiments on VAU‑Bench demonstrate significant performance gains, especially on the ECVA subset where accuracy rises from 75.81% to 90.00%.
Generalized CycleGRPO is a unified reinforcement learning framework that jointly trains region understanding and localization across spatial, temporal, and spatio‑temporal domains. It uses a multimodal large language model to generate candidate descriptions for a given region, then localizes each description to reconstruct the original region, providing verifiable rewards for both captioning and localization. The approach extends beyond image masks and boxes to video intervals and timestamped spatial evidence, and introduces the DOVE benchmark to evaluate temporal distinctiveness, achieving significant performance gains on several grounding and temporal tasks.
arXiv:2606. 04434v1 Announce Type: cross Abstract: Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks.