Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse query matrices.
hub
International journal of computer vision , volume=
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 12representative citing papers
AMUSE is a new optimizer integrating Muon orthogonalization with Schedule-Free averaging via adaptive interpolation for schedule-free anytime training that improves Pareto frontiers on vision and LLM tasks.
Empirical tests with quad-mesh filling indicate that decision regions in modern image classifiers are simply connected.
Training on automatically generated hard negative captions improves vision-language models' zero-shot detection of fine-grained image-text mismatches and robustness to noisy inputs.
GCE-MIL is a backbone-agnostic wrapper that directly optimizes MIL evidence for sufficiency, necessity, and recoverability, yielding modest gains in Macro-F1 and C-index plus more faithful patch selection across many backbones and datasets.
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
Higher-resolution observations with global-average-pooling encoders improve RL performance and generalization by enabling more localized visual attention, yielding up to 28% gains over standard Impala encoders.
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.
Stochastic image enhancement methods are shown to be variants of a shared SDE differing in drift, diffusion, terminal distributions and boundary conditions, with controlled experiments revealing no single dominant family and a new modular library released.
Representations learned by large AI models are converging toward a shared statistical model of reality.
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
citing papers explorer
-
Is Dimensionality a Barrier for Retrieval Models?
Dimension d = O(m^{-2} log n) nearly achieves the optimal margin m^rd(+∞, A) for retrieval embeddings, with matching lower bounds showing d = O(k log(n/k)) suffices and is necessary for m = Θ(k^{-1/2}) on k-sparse query matrices.
-
AMUSE: Anytime Muon with Stable Gradient Evaluation
AMUSE is a new optimizer integrating Muon orthogonalization with Schedule-Free averaging via adaptive interpolation for schedule-free anytime training that improves Pareto frontiers on vision and LLM tasks.
-
Empirical Evidence for Simply Connected Decision Regions in Image Classifiers
Empirical tests with quad-mesh filling indicate that decision regions in modern image classifiers are simply connected.
-
HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities
Training on automatically generated hard negative captions improves vision-language models' zero-shot detection of fine-grained image-text mismatches and robustness to noisy inputs.
-
GCE-MIL: Faithful and Recoverable Evidence for Multiple Instance Learning in Whole-Slide Imaging
GCE-MIL is a backbone-agnostic wrapper that directly optimizes MIL evidence for sufficiency, necessity, and recoverability, yielding modest gains in Macro-F1 and C-index plus more faithful patch selection across many backbones and datasets.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
-
Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
Higher-resolution observations with global-average-pooling encoders improve RL performance and generalization by enabling more localized visual attention, yielding up to 28% gains over standard Impala encoders.
-
HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning
HEDP uses energy regularization inspired by Helmholtz free energy plus hybrid energy-distance weighting in prompts to improve domain selection and achieve a 2.57% accuracy gain on benchmarks like CORe50 while mitigating catastrophic forgetting.
-
Unifying Deep Stochastic Processes for Image Enhancement
Stochastic image enhancement methods are shown to be variants of a shared SDE differing in drift, diffusion, terminal distributions and boundary conditions, with controlled experiments revealing no single dominant family and a new modular library released.
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.
-
Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.