Learning to Solve Complex Problems via Dataset Decomposition
arXiv:2602.20296v1 Announce Type: new Abstract: Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research explores a reverse curriculum generation approach that...
In-context Pre-trained Time-Series Foundation Models adapt to Unseen Tasks
arXiv:2602.20307v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) have demonstrated strong generalization capabilities across diverse datasets and tasks. However, existing foundation models are typically pre-trained to enhance performance on specific tasks and often struggle to generalize to unseen tasks...
QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
arXiv:2602.20309v1 Announce Type: new Abstract: Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing compute and memory demands, especially as models scale to longer horizons and larger...
CaDrift: A Time-dependent Causal Generator of Drifting Data Streams
arXiv:2602.20329v1 Announce Type: new Abstract: This work presents Causal Drift Generator (CaDrift), a time-dependent synthetic data generator framework based on Structural Causal Models (SCMs). The framework produces a virtually infinite combination of data streams with controlled shift events and time-dependent...
Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction
arXiv:2602.20344v1 Announce Type: new Abstract: Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However,...
A Generalized Apprenticeship Learning Framework for Capturing Evolving Student Pedagogical Strategies
arXiv:2602.20527v1 Announce Type: new Abstract: Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) have advanced rapidly in recent years and have been successfully applied to e-learning environments like intelligent tutoring systems (ITSs). Despite great success, the broader application of DRL...
Memory-guided Prototypical Co-occurrence Learning for Mixed Emotion Recognition
arXiv:2602.20530v1 Announce Type: new Abstract: Emotion recognition from multi-modal physiological and behavioral signals plays a pivotal role in affective computing, yet most existing models remain constrained to the prediction of singular emotions in controlled laboratory settings. Real-world human emotional experiences,...
Salesforce CEO Marc Benioff: This isn’t our first SaaSpocalypse
Salesforce reported a solid year-end earnings and then pulled out all the stops to ward off more talk of the death of its business to AI.
Anthropic acquires computer-use AI startup Vercept after Meta poached one of its founders
Seattle-based Vercept developed complex agentic tools, including a computer-use agent that could complete tasks inside applications like a person with a laptop would.
Nvidia has another record quarter amid record capex spends
"The demand for tokens in the world has gone completely exponential," Nvidia CEO Jensen Huang said about the company's earnings.
The White House wants AI companies to cover rate hikes. Most have already said they would.
Many hyperscalers have already made public commitments to cover electricity cost increases.
Wearable startup CUDIS launches a new health ring line with an AI-fueled ‘coach’
The wearable incentivizes healthy behavior with points that can be redeemed for health products.
Gemini can now automate some multi-step tasks on Android
Gemini on Android will be able to automate tasks involving rideshare requests, or grocery or food delivery, says Google.
OpenAI COO says ads will be ‘an iterative process’
COO Brad Lightcap noted that ads can add to the product experience of users if they are done right. He urged to give OpenAI a few months to see how the company fares in rolling out the product.
OpenClaw creator’s advice to AI builders is to be more playful and allow yourself time to improve
Peter Steinberger talks about the creation of his viral AI agent OpenClaw and how being more "playful" makes for a better way to learn AI coding.
Have hard-won scaling lessons to share? Take the stage at TechCrunch Founder Summit 2026
Apply to speak at TechCrunch Founder Summit 2026 by April 17 for a chance to lead a roundtable or breakout session for 1,000 founders and investors. If you’ve built, backed, or operated inside high-growth startups, your experience could shape how...
3 days left: Save up to $680 on your TechCrunch Disrupt 2026 ticket
Just 3 days left to save up to $680 on your TechCrunch Disrupt 2026 ticket. Offer ends on Friday, February 27 at 11:59 p.m. PT. Don't miss unparalleled, curated networking and valuable insights from 250+ tech leaders, and discover 300+...
Amazon’s AI-powered Alexa+ gets new personality options
Users will be able to choose from Alexa styles like Brief, Chill, or Sweet, Amazon says.
Adobe Firefly’s video editor can now automatically create a first draft from footage
Adobe Firefly is getting a new feature called Quick Cut that uses AI to edit footage to create a first draft of the final video based on user instructions.
Khosla’s Keith Rabois backs Comp, which wants to bolster HR teams with AI
The HR tech startup, which currently operates in Brazil, has raised a $17.25 million Series A.
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
arXiv:2602.19049v1 Announce Type: new Abstract: Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping methods offer limited control...
TriTopic: Tri-Modal Graph-Based Topic Modeling with Iterative Refinement and Archetypes
arXiv:2602.19079v1 Announce Type: new Abstract: Topic modeling extracts latent themes from large text collections, but leading approaches like BERTopic face critical limitations: stochastic instability, loss of lexical precision ("Embedding Blur"), and reliance on a single data perspective. We present TriTopic,...
Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models
arXiv:2602.19111v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods, especially LoRA, are widely used for adapting pre-trained models to downstream tasks due to their computational and storage efficiency. However, in the context of LoRA and its variants, the potential of...
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...
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...
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...
Hyper-KGGen: A Skill-Driven Knowledge Extractor for High-Quality Knowledge Hypergraph Generation
arXiv:2602.19543v1 Announce Type: new Abstract: Knowledge hypergraphs surpass traditional binary knowledge graphs by encapsulating complex $n$-ary atomic facts, providing a more comprehensive paradigm for semantic representation. However, constructing high-quality hypergraphs remains challenging due to the \textit{scenario gap}: generic extractors struggle...
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...
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...