Knowledge catalogue
arXiv:2609.37326v1 Announce Type: new Abstract: On-policy distillation, where a student learns from a stronger teacher's feedback on its own outputs, is a common way to pass reasoning to smaller model
arXiv:2609.36352v1 Announce Type: new Abstract: Vision-language-action (VLA) models perform well on shorter-horizon manipulation tasks but still struggle with long-horizon tasks that require multiple
arXiv:2609.37139v1 Announce Type: new Abstract: 3D content generation technology has significantly advanced the work of designers, as well as the 3D printing and gaming industries. However, it remains
arXiv:2609.37090v1 Announce Type: new Abstract: Large multimodal models (LMMs) support diverse visual understanding and reasoning tasks but are often impractical to run entirely on resource-constraine
arXiv:2609.37498v1 Announce Type: new Abstract: Wikipedia aims to provide a unified, neutral record of history, yet its independent language editions often function as distinct epistemic communities,
arXiv:2609.36230v1 Announce Type: new Abstract: We study the dynamical behavior of tokens in transformers from a control-theoretic perspective. Our model includes the feed-forward layer present after
arXiv:2609.36252v1 Announce Type: new Abstract: Closed-form recourse moves a rejected user along the unit gradient hat g of the classifier score f by the promised distance d_p=|f(x)|/|nabla f(x)|, at
arXiv:2609.37818v1 Announce Type: cross Abstract: Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguist
arXiv:2609.36816v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a cornerstone for improving the reasoning capabilities of large language models (LLMs), but the need for on-polic
arXiv:2609.36429v1 Announce Type: new Abstract: Predicting gene expression from H&E-stained histology images offers a scalable alternative to costly spatial transcriptomics, yet most existing methods
arXiv:2609.38081v1 Announce Type: new Abstract: On a single task, deep networks can learn many solutions, depending on their optimizer, training data, architecture, and hyperparameters. Many of these
arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instability
arXiv:2609.37888v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) requires models to recognize new classes over time without forgetting previously learned ones. With the rise of vision-
we comprehensively benchmarked gpt-6.1 sol on document OCR tasks. compared to gpt-6 sol from a week ago (!), we see a sizable increase in table parsing capabilities and reading order, which is pleasan
Two months after the bombshell news that a swarm of its agents had broken their containment and hacked into the computers of the AI company Hugging Face, OpenAI is still putting out fires. A steady dr
arXiv:2609.36407v1 Announce Type: new Abstract: Cross-resolution knowledge distillation aims to improve low-magnification whole- slide analysis by transferring high-magnification representations, yet
arXiv:2609.36117v1 Announce Type: new Abstract: Securing modern AI systems against backdoor attacks remains an open challenge and requires fundamentally principled estimates of the adversary's budget
arXiv:2609.37702v1 Announce Type: cross Abstract: Class Incremental Learning (Class-IL) requires models to learn new classes over time while preserving previously acquired knowledge without access to
arXiv:2609.37687v1 Announce Type: new Abstract: Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying
arXiv:2609.38059v1 Announce Type: cross Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a scal
Getting artificial intelligence into production has become the real test for enterprises. As the proof-of-concept phase ends, harder questions about cost, data and control are taking its place. That s
arXiv:2609.34374v1 Announce Type: new Abstract: Language model post-training is often bottlenecked by the need for human-collected preference data, which is expensive and difficult to scale. Reinforce
arXiv:2609.34558v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) face significant computational inefficiencies caused by the large number of visual tokens. Existing visual token pr
arXiv:2609.33256v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models map visual observations and language instructions directly to robot actions, but they do not explicitly represent th
arXiv:2609.34094v1 Announce Type: new Abstract: Identifying individual animals is crucial for effective wildlife monitoring and conservation efforts. Recent advancements in computer vision have shown
arXiv:2609.33323v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have enabled agentic systems capable of solving complex tasks through multi-turn planning, tool use, v
arXiv:2511.11257v2 Announce Type: replace-cross Abstract: The rational discovery of functional solvents remains challenging because macroscopic solvent behaviors emerge from complex many-body interact
arXiv:2609.32317v1 Announce Type: cross Abstract: As AI models grow in size and usage, their energy demands increase dramatically, raising sustainability and economic concerns. Neuromorphic hardware,
arXiv:2609.34142v1 Announce Type: new Abstract: Continuous video analytics requires accurate localization at low latency within embedded power budgets. This paper presents a hardware-software design m
As Anthropic gears up for its greatly anticipated public debut, a preview of the company's IPO filing reportedly details its mounting losses, leadership proposals to retain power, and how its AI devel
Harness distillation can train general scaffolding into a model. The harness that remains is the part tied to your tools, data, users, and environment. The post Are agent harnesses dying? What harness
arXiv:2609.32576v1 Announce Type: new Abstract: A common approach for shared autonomy blends human inputs with autonomous assistance based on the human's likely goal. However, most existing approaches
arXiv:2609.31813v1 Announce Type: cross Abstract: Dormant Awakening (DA) specializes a magnetic resonance imaging (MRI) reconstruction model by fitting a small set of zero weights to one labeled slice
arXiv:2609.32477v1 Announce Type: new Abstract: We propose a self-supervised framework designed to enhance the capability of scene text detectors in identifying and recognizing text in scenarios where
arXiv:2609.31704v1 Announce Type: cross Abstract: Large language models are increasingly used as interacting agents, but it remains unclear how robust their coordination is when public communication i
arXiv:2609.35569v1 Announce Type: cross Abstract: Large language model (LLM) serving has environmental impacts across energy consumption, carbon emission, water consumption, and biodiversity loss. Yet
arXiv:2609.35521v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) expose features that help us understand and steer language models, but faithful reconstruction does not guarantee informati
arXiv:2609.32180v1 Announce Type: new Abstract: Audio-visual segmentation (AVS) aims to segment sounding objects at the pixel level by integrating auditory and visual cues. However, existing methods a
arXiv:2609.33052v1 Announce Type: cross Abstract: Financial question answering often requires precise numerical extraction, unit handling, and arithmetic over tables and text, but applying expensive v
arXiv:2609.31996v1 Announce Type: new Abstract: Can out-of-distribution (OOD) generalization be predicted from a trained model's weights alone, without any target-domain data? Existing representationa
arXiv:2512.11352v2 Announce Type: replace Abstract: Trust prediction provides valuable support for decision-making, risk mitigation, and system security enhancement. Recently, Graph Neural Networks (G
arXiv:2609.34245v1 Announce Type: cross Abstract: LLM agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-criti
arXiv:2609.32427v1 Announce Type: new Abstract: CityToolVQA addresses the weak performance of Vision-Language Models (VLMs) on quantitative tasks in urban low-altitude visual question answering. We di
arXiv:2609.33735v1 Announce Type: new Abstract: Text-guided image editing aims to perform a desired edit while preserving source content unrelated to it. Pretrained rectified-flow models enable traini
arXiv:2602.16917v2 Announce Type: replace Abstract: Modern vision models increasingly rely on rich semantic representations that extend beyond class labels to include descriptive concepts, attributes,
arXiv:2609.32513v1 Announce Type: new Abstract: Handwritten mathematical expression recognition (HMER) refers to the task of recognizing and converting handwritten mathematics into a parsable markup l
arXiv:2609.33879v1 Announce Type: cross Abstract: Neural surrogates can accelerate large-scale optimization by replacing expensive or intractable model components with efficient learned approximations
arXiv:2609.33768v1 Announce Type: new Abstract: Multi-agent systems (MAS) have recently emerged as an effective approach for coordinating large language model (LLM)-based agents to solve complex tasks
arXiv:2609.35525v1 Announce Type: new Abstract: Principled exploration in reinforcement learning requires an agent to quantify its epistemic uncertainty and act to resolve it. Uncertainty over the val
arXiv:2509.01887v2 Announce Type: replace-cross Abstract: We study the design of interventions for causal discovery in simple structural causal models whose causal graphs are directed mixed graphs (DM
arXiv:2511.01813v3 Announce Type: replace-cross Abstract: We introduce disciplined biconvex programming (DBCP), a modeling framework for specifying and solving biconvex optimization problems. Biconvex
arXiv:2609.34408v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have shown strong promise for multimodal reasoning, yet often struggle with tasks requiring concepts beyond what is
arXiv:2609.35364v1 Announce Type: new Abstract: Many temporal link predictors summarize past interactions through learned node representations. We examine whether simple counts of recurring interactio
arXiv:2412.16633v4 Announce Type: replace Abstract: LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), a
arXiv:2609.33444v1 Announce Type: cross Abstract: A nascent family of methods that forgoes the policy gradient and reweights a supervised regression instead has garnered momentum in reinforcement lear
arXiv:2609.31633v1 Announce Type: new Abstract: In this study, a physics-enhanced neural operator framework is proposed to enhance the generalization prediction ability of the cooling layout of a turb
Opening a Model Context Protocol server, or MCP server, to customers’ AI tools is becoming standard for fintech companies, but in payments a rogue agent does not just leak data — it moves money. That
arXiv:2609.35575v1 Announce Type: new Abstract: The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of expert demonstrations and th
arXiv:2609.31890v1 Announce Type: new Abstract: Content personalization systems in financial services must ensure fair exposure across diverse offerings-a requirement driven by contractual obligations
arXiv:2609.35029v1 Announce Type: new Abstract: Hyperparameter transfer across model width can substantially reduce the cost of tuning large neural networks, but its behavior when the training horizon