Yoti comes of age as demand for digital ID grows
UK-based tech company is growing quickly but has encountered regulatory obstacles in Spain
Financial Times - Technology1 min read
AI News
Stay updated with the latest developments in Artificial Intelligence
Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings
While causal discovery methods have matured for complete data, such algorithms for handling missing values remain limited. We establish general sufficient conditions under which causal graphs remain identifiable (i.e., uniquely determined from the available data distribution) under various…
arXiv - stat.ML2 min readWhy Do VLMs Fail at Remote Physiological Measurement? Rethinking with Physiological Grounding and Numerical Alignment
Video-based remote physiological measurement (RPM) has broad applications, while Vision-Language Models (VLMs) provide a promising opportunity to enable end-to-end physiological monitoring for future human-aware intelligent systems.
arXiv - cs.CV (CV)2 min readWhose Data, Whose Benchmark? A User-Centric Framework for Auditing Evaluation Resources
Benchmarks shape how model capabilities are measured and interpreted, yet their scores can obscure whose conventions, contexts, and judgments define successful performance.
arXiv - cs.CL (NLP)2 min readWorldMemBench: A Comprehensive Benchmark for Memory of Video World Models
As video models enable longer and more realistic interactive experiences, maintaining a world consistent with its history becomes essential. This requires both preserving previously observed content and ensuring coherent world evolution over time.
arXiv - cs.CV (CV)2 min readHow to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking
Evaluation of large language models (LLMs) remains largely pre-scientific: it involves many design decisions, with little guidance on how to make them. These choices can substantially affect measured performance and, consequently, decisions about subsequent pretraining.
arXiv - cs.CL (NLP)2 min readBackpropagating Verifier Rewards Through Continuous Flow Language Models
Reinforcement learning (RL) has substantially improved the reasoning of autoregressive and discrete-diffusion language models. Language models that generate continuous token embeddings are emerging as a strong alternative, but RL post-training for them remains understudied.
arXiv cs.LG2 min readTowards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitations in spatial reasoning and perception.
arXiv - cs.CV (CV)2 min readData Density Scaling Laws for Image Self-Distillation
Current scaling law formulations suggest that increasing the number of unique samples in a dataset improves model performance, while repeated exposure to the same samples provides diminishing value. In this work, we examine this assumption for image self-distillation models.
arXiv cs.LG2 min readLearning to Select Features with Manifold Deep Unfolding PCA
Unsupervised feature selection (UFS) is of great significance in image processing and pattern recognition. Nevertheless, existing model-based methods often rely on manually tuned hyperparameters, while deep learning-based methods generally require massive training data.
arXiv - cs.CV (CV)2 min readHoli-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence
Spatial intelligence requires scalable 3D environments that are both photorealistic and semantically grounded, yet existing indoor datasets are dominated by room-scale captures and costly LiDAR acquisition.
arXiv - cs.CV (CV)2 min readVideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness
LLM system capabilities depend not only on model parameters but also on the executable harnesses that organize information acquisition, tool use, reasoning, and memory.
arXiv - cs.CV (CV)2 min readHow Inner Optimizers Shape Replica Scaling
Training large language models (LLMs) across geographically distributed and poorly interconnected compute pools or data centers has become a topic of significant interest.
arXiv cs.LG2 min readDecoupled Drift-Diffusion World Models for Consistent Future Frame Prediction
World models of visual information predict future image frames conditioned on given action sequences. This predicted scene evolution is driven by deterministic changes such as controlled motion on a robot platform, as well as stochastic changes such as rendering of manipulated objects or previously…
arXiv - cs.CV (CV)2 min readCan LLMs Access their World Knowledge for Event Prediction?
Recent work has questioned whether large language models (LLMs) can be useful for temporal event prediction. Despite vast pretrained world knowledge, LLMs often underperform simpler specialized models.
arXiv - cs.CL (NLP)2 min readPre-Trained Language Models as Zero-Shot Tools for Social Science Research
Record linkage and demographic inference from names are routine demands in social science. Most approaches to these problems require labeled training data that are difficult or costly to acquire.
arXiv - cs.CL (NLP)2 min readHigh-Probability Regret Bounds for Feel-Good Thompson Sampling
Feel-good Thompson sampling (FGTS) augments the posterior of vanilla Thompson sampling with an exploration term that favors reward functions with high predicted optimal values.
arXiv - stat.ML2 min readMinimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds
We study the minimax estimation of the pseudo-spectral gap $\gamma_{ps}$ of a Markov chain from the observation of a single trajectory. Extending earlier works on finite-state space chains by Wolfer and Kontorovich (2024), we provide an estimator in the case of a compact, continuous state-space.
arXiv - stat.ML2 min read
Showing 126 of 31,467 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts