arXiv:2606. 14507v1 Announce Type: new Abstract: Fine-tuning vision-language models to emit dense coordinate lists improves visual grounding but also changes how models serialize, repeat, and terminate structured outputs.
arXiv:2607. 10172v1 Announce Type: cross Abstract: Deploying billion-parameter Vision-Language-Action (VLA) models on industrial hardware requires fine-tuning to bridge the embodiment gap.
arXiv:2606. 30344v1 Announce Type: cross Abstract: Visual classifiers can achieve high matched-distribution accuracy while relying on low-level cues that fail under conflict or suppression.
arXiv:2606. 12105v1 Announce Type: cross Abstract: Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, processing every input at one rate.
arXiv:2506. 01850v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in instruction-following tasks by integrating pretrained visual encoders with large language models (LLMs).
arXiv:2605. 21862v2 Announce Type: replace-cross Abstract: Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone.
arXiv:2607. 12815v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extended when VLMs generate longer reasoning traces.
arXiv:2608. 15284v1 Announce Type: cross Abstract: Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable dataset construction.
arXiv:2606. 01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps.
The paper investigates why vision‑language models like LLaVA‑1.5‑7B hallucinate objects in captions and proposes a targeted fix. By ranking attention heads whose image attention drops around hallucinated words, the authors identify 32 key heads and apply a head‑sliced LoRA adapter plus an inference‑time grounding controller. On COCO images, this combined method reduces hallucinated captions from 37% to 23% and hallucinated object mentions from 15.6% to 9.6%, while also lowering object recall.
arXiv:2608. 06154v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as zero-shot controllers, but successful trajectories do not necessarily show that decisions are grounded in visual input: simulator dynamics and conservative action priors can produce favourable scores without meaningful perception.
arXiv:2607. 13205v1 Announce Type: cross Abstract: Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated attention mass, treated here as signal energy, and keeping the heaviest.
Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extended when VLMs generate longer reasoning traces. We ask whether CoT requires continued access to image tokens, or whether it mainly operates over visual information already made available earlier in the forward pass.