arXiv Machine Learning
Aug 4
Asleep at the Wheel: JEPA's Limitations in Evaluating Novel Driving Data
arXiv:2608. 01336v1 Announce Type: cross Abstract: Modern autonomous-driving fleets record far more video than human reviewers can inspect.
Rethinking Post-hoc Debiasing of Large Pretrained Models
Related stories
arXiv AI
Jun 26
Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
arXiv:2606. 27095v1 Announce Type: cross Abstract: Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initial task.
arXiv Machine Learning
Aug 11
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
arXiv:2608. 09209v1 Announce Type: cross Abstract: Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs.
Hugging Face Trending Papers
Aug 10
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs. Existing approaches either require manual specification of the feature vocabulary or automate discovery only partially, leaving the gap between dataset-level correlation and model-level exploitation unaddressed.
arXiv Machine Learning
Aug 18
Limits to scalable evaluation at the frontier: LLM as Judge won't beat twice the data
arXiv:2410. 13341v4 Announce Type: replace Abstract: High quality annotations are increasingly a bottleneck in the explosively growing machine learning ecosystem.
arXiv Computer Vision
Sep 30
OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
arXiv:2609.37331v1 Announce Type: new Abstract: Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly imp...
arXiv AI
Sep 1
Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
arXiv:2608.30699v1 Announce Type: cross Abstract: Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to...
arXiv AI
Sep 2
BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection
BiasGym is a cost‑effective, generalizable framework that injects specific biases into large language models via token‑based fine‑tuning while keeping the model frozen. It then uses two debiasing methods—Scope and Steer—to identify and suppress or redirect the components responsible for biased behavior. The framework enables consistent bias elicitation, precise localization of bias associations, and targeted debiasing without harming downstream performance, and it has been shown to reduce real‑world stereotypes such as labeling Italians as reckless drivers.
Hugging Face Trending Papers
Sep 29
OFBD: Object-Focused Background Debiasing for Long-Tailed Learning
Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly improve tail classes through re-balancing, represent...
arXiv AI
Jul 14
Algorithm Selection with Zero Domain Knowledge via Text Embeddings
arXiv:2604. 19753v2 Announce Type: replace Abstract: We propose a feature-free approach to algorithm selection: instead of hand-crafted instance features, we use pretrained text embeddings.
arXiv AI
Aug 26
Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection
The paper proposes a modular training pipeline for zero‑shot cross‑city object detection that combines a multi‑dataset pre‑training strategy with class‑agnostic objectness distillation and a domain‑resilient augmentation stream featuring a Grayworld transformation. Applied to the RF‑DETR detector, the approach reduces cross‑city distribution gaps while using only 16 GB GPU memory, achieving a 24.29‑point mAP improvement and 1st place on the AI City Challenge Track 6 leaderboard. The authors provide code and data at the referenced GitHub repository.
arXiv Machine Learning
Sep 2
SAGE: Subpopulation-Aware Generative Enhancement for Mitigating Spurious Correlations
SAGE (Subpopulation-Aware Generative Enhancement) is a two-stage generative augmentation framework designed to mitigate spurious correlations in machine learning when group labels are unavailable. It uses cluster-derived sub-labels and class labels to fine‑tune a conditional generative model and text encoder, producing synthetic data that fills underrepresented regions and creates a balanced validation set for last‑layer reweighting. Experiments show SAGE improves worst‑group accuracy to 89.5%, 85.7%, and 79.1% on Waterbirds, CelebA, and MetaShift, outperforming existing group‑label‑free baselines by up to 7.7 percentage points.