language-guided 3d motion forecasting with molmomotion
molmomotion predicts future 3d object motion from video, points, and text instructions, outperforming existing methods and aiding robotics and video generation.
aitag research
summaries filed under research
diffusion model generates irregular clinical time series with missingness
a diffusion-based method jointly models lab values and observation patterns to create realistic irregular clinical time series from mimic-iii data.
aiglm-5.2: open model for long coding tasks
glm-5.2 is an open-source model with a solid 1m-token context, improved coding, and flexible effort control, ranking highest among open models on long-horizon benchmarks.
aimodel choice matters in causal drug safety detection
a study compares classification models in the inferbert framework for pharmacovigilance, finding that simpler models can suffice and domain-specific pretraining helps.
aiediting multimodal models fails when inputs split
knowledge edits in multimodal large language models often revert to old facts when image-text pairs are separated, due to modality-specific knowledge storage.
aifixing shape-prior shortcuts in long-range fringe profilometry
a study uses mechanistic interpretability and uncertainty quantification to diagnose and repair neural network failures in single-shot 3d imaging at long distances.
aibayesian boolean matrix factorization for cancer genomics
a new bayesian method for boolean matrix factorization provides interpretable binary patterns with uncertainty estimates, applied to copy number analysis in cancer.
aitighter bounds for ai benchmark uncertainty
new concentration inequality for exchangeable sequences gives sharper error estimates when comparing ai model scores on benchmarks.
aiskill-constrained mpc for resilient supply chains
a model predictive controller balances production and worker training to handle skill shortages and disruptions in manufacturing supply chains.
aiself-evolving agent boosts legal case retrieval with bm25
a rule-based agent iteratively creates and refines query rewriting rules to improve bm25 retrieval on legal cases without training.
aikv cache as editable, composable notes
prefix caching fails when one field changes, but treating the kv cache as a notebook of memoized conclusions enables editing and composing precomputed skills.
aiai planning tool aims to halve uk home application times
google deepmind and uk government prototype uses gemini to speed up householder planning decisions by 50%.
aigoogle maps hidden hedgerows for restoration
google research releases a vectorized dataset that turns high-resolution satellite maps into an actionable inventory of fine-scale woody features like hedgerows and copses across the uk.
aistructured nonparametric vi for dependent latents
a new variational inference method uses splines to capture complex latent dependencies, moving beyond mean-field assumptions.
aiexport controls block ai bug fixing
export restrictions on claude fable 5 stem from a misinterpreted jailbreak that was actually a defensive code review request.
aipolicy regret for embedding model routing
a new algorithm tackles dynamic routing of queries to multiple embedding models under adversarial conditions and bandit feedback.
aiaudited conformal prediction for classification under distribution shift
a new method uses a small target dataset to train an audit model that improves prediction set coverage for pretrained classifiers facing unknown distribution shifts.
aiwhat makes a good explanation for ai outputs
a new definition of good explanations considers the listener's prior beliefs, highlighting why explaining large language model outputs is especially hard.
aidr-dci: scaling direct corpus interaction with dynamic workspace expansion
a new framework combines retrieval with direct corpus interaction, letting agents pull relevant documents into a local workspace for flexible search and verification without full-corpus slowdowns.
aipersonality clashes sent anthropic's models offline
axios reports internal friction and export control issues at anthropic, with key staff meeting the commerce department amid model safety concerns.
ai