In autonomous driving, perception models often struggle to generalize to new environments due to domain shifts. While unsupervised model adaptation offers a feasible solution without labor-intensive manual labeling, existing methods that rely solely on the ego-vehicle's data often lead to inferior pseudo-labeling perfo...
Ya-Nan Ma, Yi-Hang Tao, Zheng-Ru Fang et al.· 0 citations
This work introduces Contrastive Noise Alignment (CNA), a training-time method that creates dynamic, contrastive couplings by optimizing the noise representations directly, and shows theoretically that this equilibrium asymptotically preserves Gaussian structures, maintaining tractability during inference.
MCLC-NET is proposed, a multimodal continual learning framework for leaf counting that learns tasks sequentially using a memory-based strategy with a memory buffer to retain important samples from previous tasks.
Ruchi Bhatt, Pratibha Kumari, Shreya Bansal et al.· 0 citations
For the datasets and models considered, pixel-level image-fidelity metrics alone may not consistently capture the task-relevant realism of synthetic sonar observations and motivate the use of task-aware evaluation for synthetic sensor data intended for robotic perception.
Hannan Ejaz Keen, M. Fraz, Karsten Berns· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Fine-tuning a Vision-Language-Action (VLA) model for a new deployment environment is expensive, yet most methods apply uniform-capacity adapters to every network region as if every region requires equal adjustment. This paper tests that assumption on five architecturally diverse VLAs (OpenVLA-OFT, $\pi_0$, SmolVLA, DTP...
Shahram Najam Syed, Arthur Jakobsson, Prayuj Sachdev et al.· 0 citations
Open-source video generative models ship almost exclusively as PyTorch/CUDA reference implementations. This leaves Cloud TPU pods without a production-ready inference path, despite offering large, cost-effective accelerator memory pools ideal for long-sequence spatiotemporal attention. We present vidax, an open-source...
We introduce Zing-0.5, a 5B autoregressive world model designed for playability: users can explore generated worlds, influence unfolding events, and respond to the resulting feedback through joint keyboard and online text control. Our approach brings together three technical contributions: (1) Unified action and text c...
Ming-Yang Chen, Sheng Chen, Xiao-Xiao Fu et al.· 2 citations
An important component of urban accessibility, particularly for wheelchair users and people with reduced mobility, is sidewalk compliance with measurable requirements. We test whether effective width, longitudinal slope, cross slope, and pavement condition can be assessed reliably from pedestrian-level imagery using vi...
Seung Jae Lieu, Diego Morra, Chiara Cadoni et al.· 0 citations
The proposed Temperon is a plain-SGD explorer for the first 43% of the epoch budget, then one scheduled hand-off that gives the entire final cosine anneal to a SAM-wrapped Muon refiner, which matches the best full-time-SAM recipe on accuracy everywhere while reaching the hardest common target on three of the four datas...
The Learned Perceptual Image Fusion Measure (LPIFM), among the earliest learned fusion assessors trained directly on dense human A/B/Tie comparisons, provides a scalable instrument for human-aligned fusion assessment, with the preference corpus, model weights, and code publicly available.
Hao-Ran Liu, Ming-Zhe Liu, Peng Li et al.· 0 citations
SegTME-UNI2, a unified framework addressing all three requirements end-to-end of TME profiling and spatial biology research, is presented, with Qualitative validation on IGNITE NSCLC tiles shows the pipeline produces biologically coherent phenotype classifications and narratives despite inter-institutional stain variab...
Wan Siti Halimatul Munirah Wan Ahmad, F. S. Samidi, Mohammad Badal Ahmmed et al.· arXiv.org· 0 citations
Vision-language models (VLMs) can produce confident answers without relevant visual evidence, a failure mode known as mirage reasoning (Asadi et al., 2026). To that end, we study pre-release mirage detection: deciding whether a VLM answer should be released or withheld. Our model-agnostic method, Text-Conditioned Layer...
Md. Shaown Miah, S. M. Taiabul Haque, Syed Ishtiaque Ahmed et al.· 0 citations
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.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
