Sparse autoencoders inserted into VLMs and trained only for reconstruction can reliably detect adversarial attacks on images, including unseen domains and attack types.
Title resolution pending
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Presents first online L2D algorithm for multiclass classification with bandit feedback and varying experts, achieving O((n+n_e)T^{2/3}) regret generally and O((n+n_e)√T) under low noise.
NeuralBench is a new benchmarking framework for neuroAI models on EEG data that finds foundation models only marginally outperform task-specific ones while many tasks like cognitive decoding stay highly challenging.
Image editing models fail zero-shot visual planning on abstract mazes and queen puzzles but generalize after finetuning, yet still cannot match human zero-shot efficiency.
PGT generates synthetic tasks via geometric overlays on images to supply dense visual supervision, improving spatial and relational understanding in MLLMs by up to 20% on targeted benchmarks.
Weasel is a trajectory selection method that improves out-of-domain generalization for web agents while achieving 9.7-12.5x training speedups via importance-diversity optimization, AXTree pruning, and rationale style matching.
PA-BDM adapts block diffusion by switching to causal intra-block denoising and dynamically committing reliable prefixes to KV cache, yielding higher accuracy and 71.6% higher throughput than a comparable baseline on document benchmarks.
MRBTs are LLM-generated, SMT-verified behavior trees that supply modular reward functions and action masks, improving RL training efficiency and success rates on five compositional tasks over baselines.
Spherical flows on S^{d-1} with vMF noise reduce the continuity equation to a scalar ODE in cosine similarity, yielding posterior-weighted marginal velocity and score that enable ODE and predictor-corrector sampling for categorical sequences, with the posterior trained by cross-entropy and empirical
Cumulative flow maps unify few-step generative modeling for diffusion and flow models via cumulative transport and parameterization with minimal changes to time embeddings and objectives.
Biased noise sampling for rectified flows combined with a bidirectional text-image transformer architecture yields state-of-the-art high-resolution text-to-image results that scale predictably with model size.
ALLaVA creates 1.3M GPT4V-synthesized samples enabling 4B VLMs to achieve competitive results on 17 benchmarks and match 7B/13B models on some tasks.
NeuralSet is a scalable Python framework that unifies diverse neural recordings and stimuli with deep learning embeddings via metadata decoupling and lazy data extraction.
A unified training framework for mesh-based ML surrogates in CFD improves accuracy and long-horizon stability by enforcing spatial derivative consistency via multi-node prediction, using temporal cross-attention correction, and adding 3D rotary positional embeddings.
VLMs recover reliable population-level trends in climate change visual discourse on social media even when per-image accuracy is only moderate.
Proposes unifying pix and word tokens in generative LMs via per-pixel embeddings, color folding, and unsupervised pretraining, claiming strong small-model performance on limited data.
citing papers explorer
No citing papers match the current filters.