How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders
arXiv:2602.19115v1 Announce Type: new Abstract: In recent years, there has been a growing use of generative AI, and large language models (LLMs) in particular, to support both the assessment and generation of scientific work. Although some studies have shown that...
AgenticRAGTracer: A Hop-Aware Benchmark for Diagnosing Multi-Step Retrieval Reasoning in Agentic RAG
arXiv:2602.19127v1 Announce Type: new Abstract: With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction, serves as a...
Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
arXiv:2602.19157v1 Announce Type: new Abstract: Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-specific corpora. While SFT can be...
Retrieval Augmented Enhanced Dual Co-Attention Framework for Target Aware Multimodal Bengali Hateful Meme Detection
arXiv:2602.19212v1 Announce Type: new Abstract: Hateful content on social media increasingly appears as multimodal memes that combine images and text to convey harmful narratives. In low-resource languages such as Bengali, automated detection remains challenging due to limited annotated data, class...
Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering
arXiv:2602.19317v1 Announce Type: new Abstract: Personalization in Question Answering (QA) requires answers that are both accurate and aligned with users' background, preferences, and historical context. Existing state-of-the-art methods primarily rely on retrieval-augmented generation (RAG) solutions that construct personal context by...
How to Train Your Deep Research Agent? Prompt, Reward, and Policy Optimization in Search-R1
arXiv:2602.19526v1 Announce Type: new Abstract: Deep Research agents tackle knowledge-intensive tasks through multi-round retrieval and decision-oriented generation. While reinforcement learning (RL) has been shown to improve performance in this paradigm, its contributions remain underexplored. To fully understand the role of...
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework
arXiv:2602.19549v1 Announce Type: new Abstract: Visual Document Retrieval (VDR), which aims to retrieve relevant pages within vast corpora of visually-rich documents, is of significance in current multimodal retrieval applications. The state-of-the-art multi-vector paradigm excels in performance but suffers from prohibitive...
Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
arXiv:2602.19612v1 Announce Type: new Abstract: Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from pretraining or...
Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series
arXiv:2602.18473v1 Announce Type: new Abstract: Accurate analysis of medical time series (MedTS) data, such as electroencephalography (EEG) and electrocardiography (ECG), plays a pivotal role in healthcare applications, including the diagnosis of brain and heart diseases. MedTS data typically exhibit two...
Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning
arXiv:2602.18493v1 Announce Type: new Abstract: Long-context LLMs and Retrieval-Augmented Generation (RAG) systems process information passively, deferring state tracking, contradiction resolution, and evidence aggregation to query time, which becomes brittle under ultra long streams with frequent updates. We propose the Unified...
Wide Open Gazes: Quantifying Visual Exploratory Behavior in Soccer with Pose Enhanced Positional Data
arXiv:2602.18519v1 Announce Type: new Abstract: Traditional approaches to measuring visual exploratory behavior in soccer rely on counting visual exploratory actions (VEAs) based on rapid head movements exceeding 125{\deg}/s, but this method suffer from player position bias (i.e., a focus on...
AdaptStress: Online Adaptive Learning for Interpretable and Personalized Stress Prediction Using Multivariate and Sparse Physiological Signals
arXiv:2602.18521v1 Announce Type: new Abstract: Continuous stress forecasting could potentially contribute to lifestyle interventions. This paper presents a novel, explainable, and individualized approach for stress prediction using physiological data from consumer-grade smartwatches. We develop a time series forecasting model that...
The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure
arXiv:2602.18523v1 Announce Type: new Abstract: Grokking -- the abrupt transition from memorization to generalization long after near-zero training loss -- has been studied mainly in single-task settings. We extend geometric analysis to multi-task modular arithmetic, training shared-trunk Transformers on dual-task...
Audio-Visual Continual Test-Time Adaptation without Forgetting
arXiv:2602.18528v1 Announce Type: new Abstract: Audio-visual continual test-time adaptation involves continually adapting a source audio-visual model at test-time, to unlabeled non-stationary domains, where either or both modalities can be distributionally shifted, which hampers online cross-modal learning and eventually leads to...
Adaptive Time Series Reasoning via Segment Selection
arXiv:2602.18645v1 Announce Type: new Abstract: Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in a few short intervals, so the model...
Robustness of Deep ReLU Networks to Misclassification of High-Dimensional Data
arXiv:2602.18674v1 Announce Type: new Abstract: We present a theoretical study of the robustness of parameterized networks to random input perturbations. Specifically, we analyze local robustness at a given network input by quantifying the probability that a small additive random perturbation...
In-Context Planning with Latent Temporal Abstractions
arXiv:2602.18694v1 Announce Type: new Abstract: Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially observable and exhibit regime shifts...
Insertion Based Sequence Generation with Learnable Order Dynamics
arXiv:2602.18695v1 Announce Type: new Abstract: In many domains generating variable length sequences through insertions provides greater flexibility over autoregressive models. However, the action space of insertion models is much larger than that of autoregressive models (ARMs) making the learning challenging....
RadioGen3D: 3D Radio Map Generation via Adversarial Learning on Large-Scale Synthetic Data
arXiv:2602.18744v1 Announce Type: new Abstract: Radio maps are essential for efficient radio resource management in future 6G and low-altitude networks. While deep learning (DL) techniques have emerged as an efficient alternative to conventional ray-tracing for radio map estimation (RME), most...
Exact Attention Sensitivity and the Geometry of Transformer Stability
arXiv:2602.18849v1 Announce Type: new Abstract: Despite powering modern AI, transformers remain mysteriously brittle to train. We develop a stability theory that explains why pre-LayerNorm works, why DeepNorm uses $N^{-1/4}$ scaling, and why warmup is necessary, all from first principles. Our...
Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
arXiv:2602.18851v1 Announce Type: new Abstract: Attention scores in transformers are bilinear forms $S_{ij} = x_i^\top M x_j / \sqrt{d_h}$ whose maximum magnitude governs overflow risk in low-precision training. We derive a \emph{rank-aware concentration inequality}: when the interaction matrix $M =...
Issues with Measuring Task Complexity via Random Policies in Robotic Tasks
arXiv:2602.18856v1 Announce Type: new Abstract: Reinforcement learning (RL) has enabled major advances in fields such as robotics and natural language processing. A key challenge in RL is measuring task complexity, which is essential for creating meaningful benchmarks and designing effective...
VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning
arXiv:2602.18857v1 Announce Type: new Abstract: Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any task. Bayes-optimal agents achieve this, but obtaining the belief-state and performing planning are both typically...
Boosting for Vector-Valued Prediction and Conditional Density Estimation
arXiv:2602.18866v1 Announce Type: new Abstract: Despite the widespread use of boosting in structured prediction, a general theoretical understanding of aggregation beyond scalar losses remains incomplete. We study vector-valued and conditional density prediction under general divergences and identify stability conditions under...
PCA-VAE: Differentiable Subspace Quantization without Codebook Collapse
arXiv:2602.18904v1 Announce Type: new Abstract: Vector-quantized autoencoders deliver high-fidelity latents but suffer inherent flaws: the quantizer is non-differentiable, requires straight-through hacks, and is prone to collapse. We address these issues at the root by replacing VQ with a simple, principled,...
In a replay of 2019, Apple says a single desktop Mac will be manufactured in the US
Apple is still working to get favorable tariff treatment from the Trump administration.
India’s AI boom pushes firms to trade near-term revenue for users
ChatGPT and rivals are testing whether India's massive AI user boom can translate into paying customers as free offers wind down.
Meta strikes up to $100B AMD chip deal as it chases ‘personal superintelligence’
Meta is buying billions of dollars in AMD AI chips in a multiyear deal tied to a 160 million-share warrant, deepening its push to diversify beyond Nvidia and expand data center capacity.
Oura launches a proprietary AI model focused on women’s health
The model supports questions spanning the full reproductive health spectrum, from early menstrual cycles through menopause.
Final 4 days to save up to $680 on your TechCrunch Disrupt 2026 pass
Just 4 days left before savings of up to $680 on your TechCrunch Disrupt 2026 pass end on February 27 at 11:59 p.m. PT. Register to save at one of the most anticipated tech events of the year.