Category
3,920 papers
It is found that, given task-specific natural-language guidance, VLMs can estimate actuator-response relationships, resolve ambiguous observations through intervention, and actively create informative visual feedback when signals are sparse, suggesting that pretrained multimodal models can serve as important decision-m...
It is shown that general-purpose multimodal LLMs, without being trained as pathology foundation models, consistently outperform these specialized models in cross-domain histological similarity judgments, exposing a fundamental robustness gap in current pathology foundation models.
The proposed PolyTopoBench evaluates both exterior and interior rings, and benchmarks 11 representative methods, including segmentation-based polygonization pipelines, vision foundation model baselines, and specialized vector polygon generators, on two RS-image datasets covering buildings, roads, vegetation, and unvege...
Large vision-language models (LVLMs) inherit massive activations from their text-only bases: spikes where a few fixed hidden channels receive values thousands of times above the typical magnitude. The text spike systematically appears in early layers at a fixed initial position, independently of input content. Visual s...
Reach audiences
Advertise in front of researchers, engineers, and readers.
G2DA first partitions tasks into vision- and language-centric groups through gradient-guided cross-modal decoupling, then constructs modality-specific curricula based on task gradient similarity and employs bidirectional rehearsal to mitigate the recency effects introduced by sequential optimization.
REALIS provides a unified framework for measuring and improving the reliability of AI-image detectors under conditions that better reflect real-world use, and proposes a robustness protocol covering 35 transformations at five severity levels to analyze detector behavior under image processing.
MM-OPD is introduced, a multimodal on-policy self-distillation framework for symbolic-to-visual correction that transfers guidance from symbolic-conditioned behavior to the image-conditioned policy through residual token-level targets, steering the model toward correct visual evidence.
Experiments show that existing GUI-WMs exhibit systematic failures under observation-only condition, while predictive-state augmentation substantially restores state-sensitive pre- diction across evaluated WMs, preserves generative fidelity, and improves down- stream performance of GUI agents on AndroidWorld.
ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in ELBO-based RL has large impact on performance, and it also provides a unified view (as we show in this work) to understand prediction losses heuristically chosen in prior...
InterTab is a structure-aware framework for CoT reasoning over table images that interleaves chain-of-thought with tool calls that crop structure-aligned table regions, and improves the average accuracy of its backbone from 68.28% to 73.17% and achieves the best average performance among all compared methods.
DraftAttention2 is presented, a training-free framework that uses the low-resolution draft attention map to jointly select attention blocks and assign their numerical precision, and achieves a superior quality-efficiency trade-off over existing efficient video generation methods.
Feed-forward models regress dense 3D point trajectories directly from monocular video, yet the residual after global alignment is substantial and lacks a structural explanation. Measured on dynamic query points across models and datasets, the error concentrates along the view direction, while the scale correction each...
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
GPT-Lab
· gpt-lab.eu
Oct 8, 2026
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
A Blog post by H company on Hugging Face
A Blog post by Liquid AI on Hugging Face
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
