Breaking the Factorization Barrier in Diffusion Language Models
arXiv:2603.00045v1 Announce Type: new Abstract: Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the "factorization barrier": the assumption that simultaneously predicted tokens are independent. This limitation forces a trade-off: models must either sacrifice speed...
REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective
arXiv:2603.00046v1 Announce Type: new Abstract: Medical multi-modal learning is critical for integrating information from a large set of diverse modalities. However, when leveraging a high number of modalities in real clinical applications, it is often impractical to obtain full-modality observations...
Mag-Mamba: Modeling Coupled spatiotemporal Asymmetry for POI Recommendation
arXiv:2603.00053v1 Announce Type: new Abstract: Next Point-of-Interest (POI) recommendation is a critical task in location-based services, yet it faces the fundamental challenge of coupled spatiotemporal asymmetry inherent in urban mobility. Specifically, transition intents between locations exhibit high asymmetry and are...
Expert Divergence Learning for MoE-based Language Models
arXiv:2603.00054v1 Announce Type: new Abstract: The Mixture-of-Experts (MoE) architecture is a powerful technique for scaling language models, yet it often suffers from expert homogenization, where experts learn redundant functionalities, thereby limiting MoE's full potential. To address this, we introduce Expert...
MAML-KT: Addressing Cold Start Problem in Knowledge Tracing for New Students via Few-Shot Model-Agnostic Meta Learning
arXiv:2603.00137v1 Announce Type: new Abstract: Knowledge tracing (KT) models are commonly evaluated by training on early interactions from all students and testing on later responses. While effective for measuring average predictive performance, this evaluation design obscures a cold start scenario...
OSF: On Pre-training and Scaling of Sleep Foundation Models
arXiv:2603.00190v1 Announce Type: new Abstract: Polysomnography (PSG) provides the gold standard for sleep assessment but suffers from substantial heterogeneity across recording devices and cohorts. There have been growing efforts to build general-purpose foundation models (FMs) for sleep physiology, but lack...
When does Chain-of-Thought Help: A Markovian Perspective
arXiv:2603.00306v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting is a widely used inference-time technique for improving reasoning, yet its gains are uneven across tasks. We analyze when and why CoT helps by modeling the step-wise reasoning trajectory as a Markov...
Vectorized Adaptive Histograms for Sparse Oblique Forests
arXiv:2603.00326v1 Announce Type: new Abstract: Classification using sparse oblique random forests provides guarantees on uncertainty and confidence while controlling for specific error types. However, they use more data and more compute than other tree ensembles because they create deep trees...
Improving Full Waveform Inversion in Large Model Era
arXiv:2603.00377v1 Announce Type: new Abstract: Full Waveform Inversion (FWI) is a highly nonlinear and ill-posed problem that aims to recover subsurface velocity maps from surface-recorded seismic waveforms data. Existing data-driven FWI typically uses small models, as available datasets have limited...
Physics-Aware Learnability: From Set-Theoretic Independence to Operational Constraints
arXiv:2603.00417v1 Announce Type: new Abstract: Beyond binary classification, learnability can become a logically fragile notion: in EMX, even the class of all finite subsets of $[0,1]$ is learnable in some models of ZFC and not in others. We argue the...
Alibaba’s Qwen tech lead steps down after major AI push
Reactions rippled through Alibaba's Qwen team after tech lead Junyang Lin stepped down following a major model launch.
Claude Code rolls out a voice mode capability
Anthropic is stepping up its game in the AI coding space with the rollout of Voice Mode in Claude Code.
X says it will suspend creators from revenue-sharing program for unlabeled AI posts of ‘armed conflict’
Creators who break the rules will get a three-month suspension, and if they continue to violate the policy, they'll be permanently banned.
Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space
arXiv:2602.23753v1 Announce Type: new Abstract: This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured prompts to enhance semantic understanding and task adaptation...
MemEmo: Evaluating Emotion in Memory Systems of Agents
arXiv:2602.23944v1 Announce Type: new Abstract: Memory systems address the challenge of context loss in Large Language Model during prolonged interactions. However, compared to human cognition, the efficacy of these systems in processing emotion-related information remains inconclusive. To address this gap,...
The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning
arXiv:2602.23993v1 Announce Type: new Abstract: We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for feature-related data creation,...
Task-Centric Acceleration of Small-Language Models
arXiv:2602.24174v1 Announce Type: new Abstract: Small language models (SLMs) have emerged as efficient alternatives to large language models for task-specific applications. However, they are often employed in high-volume, low-latency settings, where efficiency is crucial. We propose TASC, Task-Adaptive Sequence Compression,...
Global Interpretability via Automated Preprocessing: A Framework Inspired by Psychiatric Questionnaires
arXiv:2602.23459v1 Announce Type: new Abstract: Psychiatric questionnaires are highly context sensitive and often only weakly predict subsequent symptom severity, which makes the prognostic relationship difficult to learn. Although flexible nonlinear models can improve predictive accuracy, their limited interpretability can erode...
SDMixer: Sparse Dual-Mixer for Time Series Forecasting
arXiv:2602.23581v1 Announce Type: new Abstract: Multivariate time series forecasting is widely applied in fields such as transportation, energy, and finance. However, the data commonly suffers from issues of multi-scale characteristics, weak correlations, and noise interference, which limit the predictive performance...
Selective Denoising Diffusion Model for Time Series Anomaly Detection
arXiv:2602.23662v1 Announce Type: new Abstract: Time series anomaly detection (TSAD) has been an important area of research for decades, with reconstruction-based methods, mostly based on generative models, gaining popularity and demonstrating success. Diffusion models have recently attracted attention due to...
Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning
arXiv:2602.23663v1 Announce Type: new Abstract: Multi-mode tensor time series (TTS) can be found in many domains, such as search engines and environmental monitoring systems. Learning representations of a TTS benefits various applications, but it is also challenging since the complexities...
Optimizer-Induced Low-Dimensional Drift and Transverse Dynamics in Transformer Training
arXiv:2602.23696v1 Announce Type: new Abstract: We study the geometry of training trajectories in small transformer models and find that parameter updates organize into a dominant drift direction with transverse residual dynamics. Using uncentered, row-normalized trajectory PCA, we show that a...
Bridging Dynamics Gaps via Diffusion Schr\"odinger Bridge for Cross-Domain Reinforcement Learning
arXiv:2602.23737v1 Announce Type: new Abstract: Cross-domain reinforcement learning (RL) aims to learn transferable policies under dynamics shifts between source and target domains. A key challenge lies in the lack of target-domain environment interaction and reward supervision, which prevents direct policy...
TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure
arXiv:2602.23784v1 Announce Type: new Abstract: Foundation models have transformed domains from language to genomics by learning general-purpose representations from large-scale, heterogeneous data. We introduce TradeFM, a 524M-parameter generative Transformer that brings this paradigm to market microstructure, learning directly from billions...
Inferring Chronic Treatment Onset from ePrescription Data: A Renewal Process Approach
arXiv:2602.23824v1 Announce Type: new Abstract: Longitudinal electronic health record (EHR) data are often left-censored, making diagnosis records incomplete and unreliable for determining disease onset. In contrast, outpatient prescriptions form renewal-based trajectories that provide a continuous signal of disease management. We...
InfoNCE Induces Gaussian Distribution
arXiv:2602.24012v1 Announce Type: new Abstract: Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models. A prototypical loss in contrastive training is InfoNCE and its variants. In...
pathsig: A GPU-Accelerated Library for Truncated and Projected Path Signatures
arXiv:2602.24066v1 Announce Type: new Abstract: Path signatures provide a rich representation of sequential data, with strong theoretical guarantees and good performance in a variety of machine-learning tasks. While signatures have progressed from fixed feature extractors to trainable components of machine-learning...
Cursor has reportedly surpassed $2B in annualized revenue
The four-year-old startup saw its revenue run rate double over the past three months, according to one Bloomberg source.
A married founder duo’s company, 14.ai, is replacing customer support teams at startups
14.ai also launched a consumer brand to understand how much AI can handle customer support tasks.
Anthropic’s Claude reports widespread outage
Anthropic's AI chatbot Claude experienced widespread service disruptions on Monday morning, with thousands of users reporting issues accessing the bot.