arXiv AI
Jul 8
What Images Cannot Say: Language-Guided Olfactory Representation Learning
arXiv:2607. 06402v1 Announce Type: cross Abstract: Images tell us what a scene looks like, but rarely what it would feel like to be there.
New York Smells: A Large Multimodal Dataset for Olfaction
arXiv:2511. 20544v2 Announce Type: replace-cross Abstract: While olfaction is central to how animals perceive the world, this rich chemical sensory modality remains largely inaccessible to machines.
Related stories
arXiv Machine Learning
Aug 27
A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks
The study fine‑tunes the Uni‑Mol2 molecular foundation model on the GS‑LF benchmark for multi‑label odor descriptor prediction. The resulting model matches or surpasses state‑of‑the‑art baselines on the primary benchmark and successfully transfers to four downstream olfactory tasks—including cross‑dataset prediction, odorless vs. odorous classification, enantiomer evaluation, and odor mixture discriminability—without further deep‑learning training. The enantiomer analysis demonstrates that 3D molecular representations can distinguish mirror‑image molecules, a capability lacking in 2D graph models, though predicting stereochemistry’s perceptual effects remains unresolved.
arXiv Machine Learning
Sep 14
Decoding Mixture Perception through Computational Modeling of Component Interactions
The paper introduces a bio‑inspired deep learning framework that models olfactory perception of complex chemical mixtures. It constructs neural response curves for molecule‑receptor interactions, fuses attention‑weighted multi‑receptor and concentration‑dependent multi‑molecule data, and transfers knowledge from molecular associations to improve mixture recognition. The model achieves 92.2% accuracy and offers a generalizable computational pathway from chemical blending to perceptual formation.
arXiv AI
Jun 19
Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis
arXiv:2605. 07821v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models.
arXiv Machine Learning
Sep 10
GraphNOSE: A Graph Transformer in Olfaction
arXiv:2609.05694v1 Announce Type: new Abstract: Predicting olfactory qualities from molecular structure is an open problem in chemoinformatics. Although linear models can link molecular features to o...
arXiv Computer Vision
Sep 2
CrossFeat: Bridging Imaging Modalities in Feature Descriptor Space
arXiv:2609.00272v1 Announce Type: new Abstract: Most advances in keypoint descriptions address monomodal settings, where image variations arise from viewpoint, illumination, or contrast changes. Mult...
arXiv Machine Learning
Jun 30
Meta-learning as a principle for human-like visual representations
arXiv:2606. 28399v1 Announce Type: cross Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour.
arXiv Machine Learning
Jul 15
Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
arXiv:2512. 15748v2 Announce Type: replace Abstract: Visual Species Recognition (VSR) is a fundamental task in scientific disciplines that require species-level identification, including ecology, palynology, evolutionary biology, systematics, and phylogenetics.
arXiv Computer Vision
Sep 15
VIGIL: Tackling Hallucination Detection in Image Recontextualization
arXiv:2602.14633v3 Announce Type: replace Abstract: We introduce VIGIL (Visual Inconsistency & Generative In-context Lucidity), a benchmark dataset and framework that provides a fine-grained categori...
arXiv Machine Learning
Jul 17
Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality
arXiv:2607. 14721v1 Announce Type: cross Abstract: Cross-modal learning, i.
arXiv Machine Learning
Jun 2
UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations
arXiv:2510. 13774v2 Announce Type: replace Abstract: Forecasting urban phenomena such as housing prices and public health indicators requires the effective integration of various geospatial data.
arXiv Computer Vision
Sep 24
OD3: Optimization-free Dataset Distillation for Object Detection
OD3 introduces an optimization‑free dataset distillation framework tailored for object detection. The method first iteratively places object instances in synthesized images, then screens candidates with a pre‑trained observer model to discard low‑confidence objects. Applied to MS COCO and PASCAL VOC, OD3 achieves compression ratios from 0.25% to 5% and surpasses previous detection‑focused distillation methods by over 14% on COCO mAP50 at a 1.0% compression ratio.