TRIBE v2 is a multimodal AI model that predicts human brain activity more accurately than linear encoding models and recovers established neuroscientific findings through in-silico testing.
hub
Averaging weights leads to wider optima and better generalization
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
representative citing papers
Post-processing via random selection or linear combination generates differentially private models for arbitrary privacy parameters from pre-trained models on the same dataset.
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
Neural decoder for quantum LDPC codes achieves ~10^{-10} logical error at 0.1% physical error with 17x improvement and high throughput, enabling practical fault tolerance at modest code sizes.
The Spatial Adapter equips frozen predictors with a spatially regularized orthonormal basis for residuals and derives a closed-form low-rank-plus-noise covariance for spatial prediction and kriging.
TopoGeoScore combines a torsion-inspired Laplacian log-determinant, Ollivier-Ricci curvature, and higher-order topological summaries from source embeddings, with weights learned via self-supervised invariance to geometry-preserving views, to rank checkpoints by expected OOD robustness.
MELD is a multi-task AI-text detector using auxiliary heads, uncertainty-weighted losses, EMA distillation, and pairwise ranking that reaches 99.9% TPR at 1% FPR on a new held-out benchmark while remaining competitive on the RAID leaderboard.
CPCANet deep-unfolds Common PCA to learn domain-invariant subspaces, achieving state-of-the-art zero-shot domain generalization on standard benchmarks.
Perturb-and-Correct generates epistemically diverse predictors from a single pretrained network via hidden-layer perturbations followed by affine least-squares corrections that enforce agreement on calibration data.
Graph neural networks can identify and remove unwanted beam background depositions in the Belle II calorimeter to improve hadronic clustering and reduce fake photon clusters.
The FastAT Benchmark standardizes evaluation of over twenty fast adversarial training methods under unified conditions, showing that well-designed single-step approaches can match or exceed PGD-AT robustness at lower training cost on CIFAR-10, CIFAR-100, and Tiny-ImageNet.
Training at the edge of stability causes neural network optimizers to converge on fractal attractors whose effective dimension, measured via a new sharpness dimension from the Hessian spectrum, bounds generalization error in a way not captured by prior trace or norm measures.
Muon optimizer outperforms AdamW across 17 tabular datasets when training MLPs under a shared protocol.
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
CrossAbSense oracles using frozen PLM encoders plus self- or cross-attention decoders improve prediction accuracy by 12-20% on three of five developability assays for therapeutic IgGs, with architecture choices revealing that aggregation depends on single-chain signals while stability requires heavy
MOMO merges sensor-specific models from three Mars orbital instruments at matched validation loss stages to form a foundation model that outperforms ImageNet, Earth observation, sensor-specific, and supervised baselines on nine Mars-Bench tasks.
The paper proposes Trajectory Regularized Merging (TRM) to enable storage-free model merging in continual learning by optimizing in an augmented trajectory subspace with task alignment, prediction consistency, and gradient responsiveness objectives, claiming SOTA results.
A new neural network stabilizes features for rare chest X-ray diseases via momentum anchoring and multi-scale fusion on EfficientNet, achieving 0.8682 AUC on ChestX-ray14.
Phoenix-VL 1.5 Medium is a 123B-parameter natively multimodal model that reaches state-of-the-art results on Singapore multimodal, legal, and policy benchmarks after localized training on 1T+ tokens while staying competitive on global benchmarks.
LLMs struggle with abstract meaning comprehension on SemEval-2021 Task 4 more than fine-tuned models, and a new bidirectional attention classifier yields small accuracy gains of 3-4%.
citing papers explorer
-
FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods
The FastAT Benchmark standardizes evaluation of over twenty fast adversarial training methods under unified conditions, showing that well-designed single-step approaches can match or exceed PGD-AT robustness at lower training cost on CIFAR-10, CIFAR-100, and Tiny-ImageNet.