Knowledge catalogue
arXiv:2609.23409v1 Announce Type: new Abstract: Cache-based test-time adaptation improves CLIP predictions by storing and retrieving examples from the target stream while keeping the model frozen. How
arXiv:2609.23997v1 Announce Type: new Abstract: Multi-robot collaboration could enable more efficient and scalable solutions to complex robotic tasks, but collaboration under partial observability rem
arXiv:2502.06726v4 Announce Type: replace-cross Abstract: We derive first-order Pontryagin optimality conditions for stochastic optimal control with deterministic controls for systems modeled by rough
arXiv:2609.23466v1 Announce Type: new Abstract: Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at ever
arXiv:2609.23113v1 Announce Type: new Abstract: Foundation models (FMs) have expanded task and motion planning (TAMP) to manipulation problems specified through language and visual observations. Howev
arXiv:2609.22486v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on external sources when answering questions that require proprietary information or up-to-date live we
arXiv:2609.22630v1 Announce Type: new Abstract: Subjective user experience is important to human-robot interaction, but the outcomes users value, and how those preferences vary across individuals and
arXiv:2508.01661v2 Announce Type: replace Abstract: Amodal segmentation aims to recover complete object shapes, including occluded regions, serving as an essential technique for user-centric multimedi
arXiv:2609.23248v1 Announce Type: new Abstract: A fundamental challenge in deploying vision models is domain shift, which arises when training and test data follow different distributions, leading to
arXiv:2609.24111v1 Announce Type: cross Abstract: Test-time adaptation (TTA) addresses distribution shift using only unlabeled test data. Existing methods typically adapt pretrained models by updating
arXiv:2609.22888v1 Announce Type: new Abstract: Online post-training of vision-language-action (VLA) models requires efficient use of robot interaction and reliable policy improvement from continually
arXiv:2609.22123v1 Announce Type: new Abstract: Multi-station multivariate weather forecasting aims to forecast future weather variables at multiple weather stations from historical surface observatio
arXiv:2609.22158v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length,
arXiv:2609.22534v1 Announce Type: cross Abstract: Strategic classification studies how a decision maker should choose a classifier when the agents being classified can adjust their features in respons
arXiv:2609.22257v1 Announce Type: cross Abstract: Producing task-specific large language models requires discovering effective training strategies through experimentation. Automated fine-tuning system
arXiv:2609.23580v1 Announce Type: new Abstract: Reactive vision--language--action (VLA) models struggle with long-horizon manipulation when visually similar observations can correspond to different ac
arXiv:2509.01167v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can ingest only a limited number of video frames, making frame selection a practical necessity. But do current V
arXiv:2609.22156v1 Announce Type: new Abstract: Speculative decoding in Mixture-of-Experts (MoE) models faces the problem of unstable verification cost caused by input-dependent expert loading. To stu
arXiv:2609.24379v1 Announce Type: new Abstract: Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entangle
**Summary:** NVIDIA Topograph discovers and normalizes cluster topology from cloud APIs or on‑prem fabric systems into a common model that is published as Kubernetes node labels, Slurm configuration,
arXiv:2406.03894v2 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due
arXiv:2605.24625v2 Announce Type: replace Abstract: Ultra-low-field (ULF) MRI offers portable and accessible neuroimaging but suffers from reduced signal-to-noise ratio and limited spatial resolution
arXiv:2609.24265v1 Announce Type: cross Abstract: Unsupervised anomaly detection (UAD) aims to localize abnormal regions in medical scans without pixel-level annotations. A typical strategy seeks to r
arXiv:2609.23372v1 Announce Type: new Abstract: Accurate multi-user localization is challenging in complex urban environments, where wireless measurements can become ambiguous under noise, blockage, a
arXiv:2609.22462v1 Announce Type: new Abstract: Vision-language-action (VLA) models enable increasingly general-purpose robotic manipulation, but such learned policies do not provide safety guarantees
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction ofte
arXiv:2609.23366v1 Announce Type: new Abstract: Recurrent models must preserve information that changes future behavior while suppressing hidden-state error. These objectives conflict: contraction imp
arXiv:2609.24862v1 Announce Type: new Abstract: Agentic time series forecasting concerns systems whose underlying mechanisms evolve, making the relative effectiveness of numerical models, reasoning st
arXiv:2609.23117v1 Announce Type: new Abstract: Whitening a foundation-model embedding and using its squared norm as a training-free likelihood surrogate is motivated by the observation that whitened
arXiv:2609.23260v1 Announce Type: new Abstract: Subliminal Learning (SL) is a recently identified phenomenon in which a student model acquires downstream task capabilities by matching seemingly unrela
arXiv:2609.22716v1 Announce Type: new Abstract: Image-to-LiDAR registration estimates the camera pose of an image with respect to a LiDAR point cloud. It has diverse applications in autonomous driving
arXiv:2609.21516v1 Announce Type: new Abstract: Active reconstruction requires efficient active view selection to achieve high-quality reconstruction within limited onboard computational resources. Ex
arXiv:2609.21192v1 Announce Type: new Abstract: Organizations deploying agentic artificial intelligence must determine more than whether a model is trustworthy; they must establish what to validate, c
arXiv:2609.21378v1 Announce Type: new Abstract: Reinforcement learning has substantially improved large language model (LLM) agents in verifiable domains, but remains difficult to apply to open-ended
arXiv:2609.21940v1 Announce Type: new Abstract: Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing mem
arXiv:2512.24493v3 Announce Type: replace-cross Abstract: Control barrier functions for port-Hamiltonian systems inherit model uncertainty when the Hamiltonian is learned from data. We show how to pro
arXiv:2609.20844v1 Announce Type: new Abstract: Deepresearch (DR) agents interact with real-world web environments through multi-turn search and visit, causing their contexts to grow rapidly over time
arXiv:2609.21761v1 Announce Type: new Abstract: We present CRISP (Contact-RIch Simulation Platform), a high-fidelity physics engine tailored for complex multi-contact simulations such as tight-toleran
arXiv:2609.21327v1 Announce Type: cross Abstract: Quantile-based reinforcement learning provides an interpretable approach to risk-sensitive decision-making by optimizing a prescribed quantile of the
arXiv:2609.05799v2 Announce Type: replace Abstract: In streaming simultaneous speech translation, the speech translation system is trained to learn a read-write policy that alternates between consumin
arXiv:2609.21057v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training without sharing raw data, but its performance degrades under non-IID data and stochastic cl
arXiv:2609.21349v1 Announce Type: cross Abstract: Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existin
arXiv:2609.21432v1 Announce Type: new Abstract: Post-training plays a pivotal role in enhancing the reasoning capabilities and task-specific expertise of large language models (LLMs). Despite recent a
arXiv:2609.21277v1 Announce Type: new Abstract: How many human judgments does a panel of language models represent? The answer depends on what is matched. We audit categorical judge panels against emp
arXiv:2609.21208v1 Announce Type: new Abstract: Self-play methods that co-train a single language model as both coder and test author promise to move code-generation RL beyond fixed test suites, but t
arXiv:2512.06201v3 Announce Type: replace Abstract: We introduce K2-V2, a 360-open LLM built from scratch as a superior base for reasoning adaptation, in addition to functions such as conversation and
arXiv:2609.22041v1 Announce Type: new Abstract: Reinforcement learning is increasingly used to align image generators with reward signals, and Flow-GRPO recently extended this paradigm to flow-matchin
arXiv:2609.21624v1 Announce Type: new Abstract: Problematic internet use affects a growing share of the population, yet common interventions, e.g., time limits, blocking, forced breaks, are coercive a
arXiv:2609.21519v1 Announce Type: new Abstract: Artificial Intelligence (AI) is becoming a fundamental design principle of future AI-native communication networks, enabling autonomous resource managem
arXiv:2609.21894v1 Announce Type: new Abstract: We introduce an iterative framework that automates the extraction of interpretable, schema-bound categorical features from unstructured text for tabular
lots of them! Reality is that LLM APIs are far from being the best way to do AI for 90% of use cases in the real world (they're too overkill, slow, expensive, hard to control,...). We will discover th
arXiv:2609.21164v1 Announce Type: new Abstract: Integrating diverse data modalities --- such as clinical notes, laboratory results, and medical imaging --- is essential for advancing clinical decision
arXiv:2609.21095v1 Announce Type: new Abstract: We present MarsFM, an image-conditioned latent flow-matching model for local Martian relief estimation from single-band HiRISE RED orthoimagery. The met
arXiv:2602.07036v2 Announce Type: replace-cross Abstract: Audio large language models (AudioLLMs) enable instruction following over speech and general audio, but progress is limited by the scarcity of
My dream was literally like watching a tech horror movie. I don't think I've ever woken up before saying 'WTF....' like this before. The AI systems began seizing and corrupting all manner of connected
One hope for Tinker is that it can handle all the ML infra for posttraining for (approximately) everyone. So, curious, what prevents you from using Tinker for all your posttraining needs? Speed? Cost?
arXiv:2609.21609v1 Announce Type: cross Abstract: Model-free reinforcement learning can acquire contact-rich robotic manipulation skills through trial-and-error interaction, but it often requires the
EXL built an AI-powered Medical intelligent document processing (IDP) solution on AWS, combining IDP with domain-specific large language models on Amazon SageMaker and Amazon Bedrock to extract, summa
arXiv:2609.21960v1 Announce Type: cross Abstract: Masked discrete diffusion models are commonly accelerated using the so-called tau-leaping discretization method, which reveals several coordinates in
arXiv:2609.21676v1 Announce Type: cross Abstract: We present the Spoken Wikipedia Presentation Corpus, an extension of the Spoken Wikipedia Corpora featuring LLM-generated slide decks for multimodal A