Experiments show that VG-TIE is competitive with other tabular-to-image methods while providing interpretability on feature importance and ranking similar to intrinsic interpretable methods, and highlights the potential of the proposed image-based transformation to provide an effective framework that expands the use of...
David Chushig-Muzo, L. López-Ramos, Ángeles Rodríguez de Cara et al.· 0 citations
Albireo is presented, a detector-agnostic, codec-free adaptive inference framework that wraps off-the-shelf detectors and decides when detector invocation can be safely skipped based on scene content and per-object temporal state, requiring no detector modification or retraining.
Amir Taherin, José Cano, Bin Ren et al.· 0 citations
Flow-Based Distribution Matching is introduced, a non-adversarial framework that learns this reference-directed geometry through spherical conditional velocity regression that achieves performance nearly on par with DM and remains competitive with existing SSL methods.
Yu-Ling Jiao, Wen-Sen Ma, Hou-Duo Qi et al.· 0 citations
Unified vision-language models (VLMs) that tokenize images through a vector-quantized (VQ) codebook routinely hallucinate objects on grounded yes/no benchmarks, yet existing decoding-time fixes treat this as generic miscalibration without an architectural account. Using activation patching across twenty-five models spa...
Shamanthak Hegde, Xiang-Rui Liu, Maitreya Patel et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Rift is presented, a two-stage system that performs query-conditioned tile pruning followed by elastic prefill to reduce token budget and reduces energy by 78% and latency by 69%, while increasing accuracy from 45% to 73%.
Ishani Janveja, David Zhang, Seoyul Oh et al.· 0 citations
Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided methods mainly improve where image and language features interact but generally retain a single learned update pathway across all image-text pairs. We propose MRSeg, a pa...
Md. Maklachur Rahman, M. H. Al Banna, Saraf Anjum et al.· 0 citations
Encoding input coordinates with sinusoidal functions into multi-layer perceptrons (MLPs) has proven effective for implicit neural representations (INRs) of surfaces defined as zero-level sets. However, existing methods often struggle to balance training efficiency, rendering speed, and noise robustness: single-MLP appr...
Vin\'icius da Silva, Isabelle Melo, Matheus Bessa et al.· 0 citations
This work introduces UltraBench 2, a comprehensive benchmark with wide anatomical and task coverage, and a focus on standardization, reproducibility, and ease-of-use, and demonstrates that ultrasound-specific pretraining still leads on classification, but that state-of-the-art general-purpose models have drawn level on...
Ashwath Radhachandran, Adam Tupper, Christian Gagné et al.· 0 citations
SpiKFAX is proposed, a second-order optimization method that formulates a computationally tractable, Kronecker-factored approximation of the Fisher information matrix specifically adapted to the structure of SNNs.
The TAM-Chain framework proves to be a highly effective, safe, and adaptable solution for digital pathology workflows, successfully harmonizing automated diagnostic efficiency with stringent biological safety.
Recent advances in diffusion models highlight the importance of representation regularization for improving sample quality and training efficiency. However, commonly used regularization methods often overlook the built-in conditions (such as labels or texts) which directly determine the generation target. In this work,...
SOV-CAD is proposed, a framework that formulates CAD reconstruction as a sequential decision-making task and employs offline reinforcement learning with a Decision Transformer architecture that incorporates continuous visual feedback guided by geometric alignment rewards, resulting in a more accurate and human-like mod...
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
