A NeurIPS paper looks inside looped language models and finds that each pass through the shared block repeats the same processing stages a normal Transformer runs once. Whether those stages hold steady depends on a few design choices.
Monash and German researchers prune the Hydra and Quant time series classifiers, cutting inference energy by up to 70% with only a small loss in accuracy, and show that hardware choice can change which model looks best.
A revised MIT/Oxford paper shows that tuning AI classifiers for accuracy can quadruple worst-case liability, and proposes insurance contracts that force safer decision thresholds.
MI-Pruner decides which image tokens to drop by measuring how much each one shares with the text prompt. It never reads attention maps, so it can be added to off-the-shelf multimodal models without changing them.
In a 10-person exoskeleton pilot, walking patterns fitted to each user scored no better than an averaged pattern. How long people had been in the device mattered more.
Pooling more training corpora can make speech deepfake detectors worse. IDFE adds a corpus classifier with gradient reversal so the model can't lean on dataset quirks, and it cuts pooled error by up to 20%.
Frontier coding agents found 'significant' effects in data that contained none in up to 98% of runs. A new replay test corrects the p-values by measuring the agent's own selection bias.
A three-sensor neural network trained on simulation data reconstructs the full temperature and flow fields of a real natural circulation nuclear test rig.
A pixel-space diffusion transformer from CMU and Rice learns to merge related image patches by itself. It scores 1.48 FID on ImageNet and needs 2.4× less training compute than JiT to reach the same quality.
A multi-agent reinforcement learning system from DeepReinforce swept three consecutive live Codeforces rounds, outperforming every human including legendary grandmasters.
A new paper argues that self-attention works like the Dyson equation from many-body physics, which would explain why sum-pooling models break down on correlated quantum states.
ENIGMA-360 pairs 180 headset videos with 180 synced fixed-camera videos of real repair work. Top video models break down when they have to switch between the two views.
A new Transformer layout runs full blocks side by side. In small MoE tests it beats standard stacks on quality at matched compute and decodes up to 51% faster.
FedBNN trains one-bit neural networks across federated devices using rotation-aware binarization, cutting FLOPs up to 58x and memory 32x with competitive accuracy.
A new review paper shows that noise contrastive estimation, bridge sampling, and importance sampling are the same algorithm in disguise, and uses that insight to build better estimators for energy based models.
A hybrid quantum-classical LSTM with fewer than 300 parameters gets within about 1% of deep-learning AUC on a particle-physics benchmark while training on only 20K rows.