BICL uses biased non-uniform transition matrices to generate constrained complementary labels, enabling effective learning and over sevenfold accuracy gains on many-class image datasets.
hub Mixed citations
A simple framework for contrastive learning of visual representations
Mixed citation behavior. Most common role is method (50%).
26
Pith papers citing it
Method
50% of classified citations
hub tools
citation-role summary
method 5
background 4
baseline 1
citation-polarity summary
representative citing papers
MaxSketch achieves O~(log n / ε²) memory for (1+ε)-approximate distinct counting in streams with geometric structure via max-linear random projections.
SpurAudio benchmark shows state-of-the-art few-shot audio classifiers suffer large performance drops when background correlations are disrupted, even in large pretrained models.
SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.
LatentUMM proposes dual latent alignment at modality and capacity levels plus latent dynamics stabilization to reduce semantic drift and improve consistency in unified multimodal models.
Latent prediction video models exhibit a distinct robustness profile across corruption, occlusion, fine-grained discrimination, and temporal sensitivity compared to other self-supervised video models when used as world models.
Crys-JEPA introduces a joint embedding predictive architecture that creates an energy-aware latent space, enabling embedding-based stability screening and a refinement pipeline that yields up to 72.7% gains on the V.S.U.N. metric for crystal generation.
ConSPO is a new contrastive sequence-level policy optimization method that addresses GRPO limitations via length-normalized log-probability scores and InfoNCE-style objectives, outperforming baselines on reasoning benchmarks.
FuTCR improves new-class panoptic quality by up to 28% in continual panoptic segmentation by discovering future-like regions in background areas and applying targeted contrast and repulsion to restructure representations.
WavesFM uses hierarchical SSL to pretrain a segment encoder on short waveforms followed by a temporal encoder on multi-day sequences, outperforming prior methods on 58 tasks after training on over 12 million hours of data from hundreds of thousands of people.
DeCIR improves projection-based zero-shot composed image retrieval by decoupling endpoint and semantic transition alignment with separate low-rank adapters merged by LRDM, showing gains on CIRR, CIRCO, FashionIQ, and GeneCIS.
DistillGaze reduces median gaze error by 58.62% on a 2000+ participant dataset by distilling foundation models into a 256K-parameter on-device model using synthetic labeled data and unlabeled real data.
Drifting models outperform diffusion, CNN, VAE, and GAN baselines in MRI-to-CT synthesis on two pelvis datasets with higher SSIM/PSNR, lower RMSE, and millisecond one-step inference.
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.
A parameter-efficient plug-in framework adds structurally compatible long-sequence processing and semantically informed temporal modeling to extend pretrained 10-second ECG foundation models to longer variable-length inputs.
SPEAR enables online federated LLM fine-tuning by using feedback-guided self-play to create contrastive pairs trained with maximum likelihood on correct completions and confidence-weighted unlikelihood on incorrect ones, outperforming baselines without ground-truth contexts.
BenchHAR finds that hybrid reconstruction-plus-contrastive SSL with CNN encoders generalizes best for sensor HAR but overall performance on unseen distributions remains unsatisfactory.
ShellfishNet is a new benchmark of 8,691 images across 32 mollusc taxa for evaluating vision models on real-world underwater ecological monitoring tasks including robustness to degradation.
Pan-FM learns balanced representations across seven organs by adaptively masking dominant organs during pre-training, yielding stronger disease prediction and missing-organ robustness than single-organ or naive multimodal baselines on UK Biobank.
ConvFormer3D-TAP classifies six cine CMR views at 96% accuracy using 3D conv tokenization, multiscale attention, and uncertainty-aware multi-clip fusion on 150k sequences.
GaiaFlow combines semantic-guided diffusion tuning with early-exit and quantization methods to lower carbon emissions in neural information retrieval while maintaining competitive effectiveness.
Basic dataset creation, embedding learning, and evaluation tasks on Kuhn and Leduc Poker demonstrate that useful behavioral representations appear in the learned embeddings.
HARNESS-LM uses teacher fine-tuning, L2 query alignment, and contrastive refinement to distill large SLM retrievers into compact models that recover 98% precision with up to 27x lower latency on Bing Ads benchmarks.
A task-oriented review of medical-image SSL arguing that pretext tasks should be chosen to match downstream tasks and modalities, not used one-size-fits-all.
citing papers explorer
-
Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
BICL uses biased non-uniform transition matrices to generate constrained complementary labels, enabling effective learning and over sevenfold accuracy gains on many-class image datasets.
-
MaxSketch: Robust Distinct Counting in Streams via Random Projections
MaxSketch achieves O~(log n / ε²) memory for (1+ε)-approximate distinct counting in streams with geometric structure via max-linear random projections.
-
SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
SpurAudio benchmark shows state-of-the-art few-shot audio classifiers suffer large performance drops when background correlations are disrupted, even in large pretrained models.
-
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.
-
LatentUMM: Dual Latent Alignment for Unified Multimodal Models
LatentUMM proposes dual latent alignment at modality and capacity levels plus latent dynamics stabilization to reduce semantic drift and improve consistency in unified multimodal models.
-
Latent Video Prediction Learns Better World Models
Latent prediction video models exhibit a distinct robustness profile across corruption, occlusion, fine-grained discrimination, and temporal sensitivity compared to other self-supervised video models when used as world models.
-
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
Crys-JEPA introduces a joint embedding predictive architecture that creates an energy-aware latent space, enabling embedding-based stability screening and a refinement pipeline that yields up to 72.7% gains on the V.S.U.N. metric for crystal generation.
-
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
ConSPO is a new contrastive sequence-level policy optimization method that addresses GRPO limitations via length-normalized log-probability scores and InfoNCE-style objectives, outperforming baselines on reasoning benchmarks.
-
FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
FuTCR improves new-class panoptic quality by up to 28% in continual panoptic segmentation by discovering future-like regions in background areas and applying targeted contrast and repulsion to restructure representations.
-
WavesFM: Hierarchical Representation Learning for Longitudinal Wearable Sensor Waveforms
WavesFM uses hierarchical SSL to pretrain a segment encoder on short waveforms followed by a temporal encoder on multi-day sequences, outperforming prior methods on 58 tasks after training on over 12 million hours of data from hundreds of thousands of people.
-
Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
DeCIR improves projection-based zero-shot composed image retrieval by decoupling endpoint and semantic transition alignment with separate low-rank adapters merged by LRDM, showing gains on CIRR, CIRCO, FashionIQ, and GeneCIS.
-
Rapidly deploying on-device eye tracking by distilling visual foundation models
DistillGaze reduces median gaze error by 58.62% on a 2000+ participant dataset by distilling foundation models into a 256K-parameter on-device model using synthetic labeled data and unlabeled real data.
-
MRI-to-CT synthesis using drifting models
Drifting models outperform diffusion, CNN, VAE, and GAN baselines in MRI-to-CT synthesis on two pelvis datasets with higher SSIM/PSNR, lower RMSE, and millisecond one-step inference.
-
CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model
CodeBrain introduces a decoupled TFDual-Tokenizer and multi-scale EEGSSM architecture for an EEG foundation model pretrained on a large corpus, claiming strong generalization across eight downstream tasks and ten datasets.
-
Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons
A parameter-efficient plug-in framework adds structurally compatible long-sequence processing and semantically informed temporal modeling to extend pretrained 10-second ECG foundation models to longer variable-length inputs.
-
Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback
SPEAR enables online federated LLM fine-tuning by using feedback-guided self-play to create contrastive pairs trained with maximum likelihood on correct completions and confidence-weighted unlikelihood on incorrect ones, outperforming baselines without ground-truth contexts.
-
BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognition
BenchHAR finds that hybrid reconstruction-plus-contrastive SSL with CNN encoders generalizes best for sensor HAR but overall performance on unseen distributions remains unsatisfactory.
-
ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs
ShellfishNet is a new benchmark of 8,691 images across 32 mollusc taxa for evaluating vision models on real-world underwater ecological monitoring tasks including robustness to degradation.
-
Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness
Pan-FM learns balanced representations across seven organs by adaptively masking dominant organs during pre-training, yielding stronger disease prediction and missing-organ robustness than single-organ or naive multimodal baselines on UK Biobank.
-
ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines
ConvFormer3D-TAP classifies six cine CMR views at 96% accuracy using 3D conv tokenization, multiscale attention, and uncertainty-aware multi-clip fusion on 150k sequences.
-
GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search
GaiaFlow combines semantic-guided diffusion tuning with early-exit and quantization methods to lower carbon emissions in neural information retrieval while maintaining competitive effectiveness.
-
Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games
Basic dataset creation, embedding learning, and evaluation tasks on Kuhn and Leduc Poker demonstrate that useful behavioral representations appear in the learned embeddings.
-
HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
HARNESS-LM uses teacher fine-tuning, L2 query alignment, and contrastive refinement to distill large SLM retrievers into compact models that recover 98% precision with up to 27x lower latency on Bing Ads benchmarks.
-
Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Task-Oriented Review with Practical Design Guidelines
A task-oriented review of medical-image SSL arguing that pretext tasks should be chosen to match downstream tasks and modalities, not used one-size-fits-all.
-
A Gesture-Based Visual Learning Model for Acoustophoretic Interactions using a Swarm of AcoustoBots
OpenCLIP-based gesture classification with linear probing controls AcoustoBot swarms at 87.8% accuracy and 3.95 s latency in controlled tests.
-
Representation learning from OCT images
A structured survey of representation learning methods for retinal OCT image analysis, covering supervised, self-supervised, generative, multimodal, and foundation model approaches along with datasets and open problems.