Knowledge catalogue
arXiv:2610.06932v1 Announce Type: new Abstract: Cache-based test-time adaptation (TTA) for vision-language models is often hindered by background bias in global representations and unreliable entropy-
arXiv:2610.07863v1 Announce Type: cross Abstract: Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with st
arXiv:2610.07720v1 Announce Type: new Abstract: Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing d
arXiv:2610.07894v1 Announce Type: new Abstract: Large language models (LLMs) are expected to answer questions faithfully based on the provided context, abstaining when the context information is insuf
arXiv:2512.23073v2 Announce Type: replace-cross Abstract: Fine-tuning has become the dominant paradigm for adapting Vision-Language Models (VLMs), yet most approaches rely on explicit weight updates t
arXiv:2610.07834v1 Announce Type: new Abstract: Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster.
arXiv:2610.07217v1 Announce Type: cross Abstract: Despite its promise for scaling robot learning, egocentric manipulation data is still scarce today. Collection at scale requires vertically integratin
arXiv:2610.07485v1 Announce Type: new Abstract: We study estimating rare-event probabilities I = P(g(mathbf{X}) > gamma) with mathbf{X} sim N(oldsymbol{mu}, oldsymbol{Sigma}) and general g : R^d o R.
arXiv:2610.08539v1 Announce Type: new Abstract: Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis. Existing approaches mainly follow three paradigm
Disclosure first: I work at Vstorm and I build AgenticOS, an open-source (Apache-2.0), self-hosted platform for building AI agents in a browser. This post was drafted with an LLM's help and edited by
arXiv:2610.07532v1 Announce Type: cross Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks incl
arXiv:2610.08093v1 Announce Type: cross Abstract: Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-qu
arXiv:2606.12671v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used to detect whether AI-generated images contain visible artifacts, yet their ability to analyze su
arXiv:2610.07324v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are trained on large collections of time series datasets that span various morphologies and domains. This settin
NVIDIA cuOpt’s Multi‑GPU Primal‑Dual Hybrid Gradient (mPDLP) solver distributes linear programming problems across NVLink‑connected GPUs, cutting per‑GPU peak memory by up to six times and handling up
arXiv:2610.07346v1 Announce Type: new Abstract: Repeated evaluation and differentiation of Signal Temporal Logic (STL) robustness can become a computational bottleneck in robot planning and control. S
arXiv:2610.07846v1 Announce Type: cross Abstract: The scenario approach is a well-established statistical framework for data-driven decision-making. In particular, in data-driven optimization, the sce
arXiv:2610.08678v1 Announce Type: cross Abstract: Speculative decoding accelerates inference for a large language model (LLM), referred to as the target model, by first using a smaller model, referred
arXiv:2610.07335v1 Announce Type: cross Abstract: Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous ag
arXiv:2610.08659v1 Announce Type: cross Abstract: Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-base
arXiv:2610.08668v1 Announce Type: cross Abstract: Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prio
arXiv:2610.08244v1 Announce Type: new Abstract: Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models however largely stop at perception
arXiv:2610.07060v1 Announce Type: new Abstract: Despite substantial progress in short-to-medium-range weather forecasting, predicting high-impact events such as flash droughts remains a key challenge
arXiv:2610.07645v1 Announce Type: cross Abstract: Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this lea
arXiv:2610.07093v1 Announce Type: new Abstract: The rapid proliferation of heterogeneous data sources within the Internet of Things (IoT) across domains such as smart cities, energy management, and en
arXiv:2610.07652v1 Announce Type: cross Abstract: The ability to interact with articulated objects is essential for embodied intelligent systems, but collecting large-scale real-world demonstrations f
arXiv:2610.07121v1 Announce Type: new Abstract: Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based t
arXiv:2610.08021v1 Announce Type: new Abstract: Simulation-based inference (SBI) has become a powerful approach to Bayesian inference in complex scientific models whose likelihoods are difficult or im
arXiv:2511.20718v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks
arXiv:2610.08649v1 Announce Type: new Abstract: Video-language models are ranked by multiple-choice accuracy on frames from a uniform grid. The grid has two parameters, a rate and a phase, and benchma
arXiv:2610.07756v1 Announce Type: new Abstract: Vision-language-action (VLA) models increasingly rely on diffusion- or flow-matching-based action heads to generate continuous robot actions. These acti
arXiv:2610.07625v1 Announce Type: cross Abstract: Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay
arXiv:2610.07348v1 Announce Type: cross Abstract: Training large language models (LLMs) is resource-intensive, and adapting them for diverse deployment scenarios with varying computational constraints
arXiv:2610.07470v1 Announce Type: cross Abstract: Combinatorial Thompson sampling (CTS) draws independent posterior samples for every arm, so its exploration dynamics ignore any relation among arms. W
arXiv:2610.08018v1 Announce Type: new Abstract: Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must f
arXiv:2610.07332v1 Announce Type: cross Abstract: Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structu
arXiv:2610.08098v1 Announce Type: cross Abstract: AI agents increasingly rely on modular third-party 'skills' that are dynamically selected by skill routers to execute complex tasks. While recent stud
arXiv:2610.07559v1 Announce Type: new Abstract: Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with
arXiv:2610.06994v1 Announce Type: cross Abstract: Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate
arXiv:2610.05437v2 Announce Type: replace Abstract: Computer-use agents need to capture procedural knowledge of how people use software. User telemetry offers a scalable source of this knowledge. Howe
The Windows launch event today has mentioned 'local AI' 41 times (so far) 🤯 Media It is very cool to see llama.cpp on the big stage in todays Windows event! The software and hardware stacks are finall
arXiv:2610.07803v1 Announce Type: new Abstract: Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they of
arXiv:2610.08205v1 Announce Type: cross Abstract: Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-
arXiv:2610.07004v1 Announce Type: new Abstract: Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for s
arXiv:2610.07043v1 Announce Type: cross Abstract: Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discrepancies between learner and samp
I don't know if anyone else has ran into these issues but when using Qwen Flash Next, my confidence in it at iq4_xs is high but not 100%. I notice it not following instructions, hallucinating more oft
arXiv:2610.07570v1 Announce Type: new Abstract: In clinical practice, agreement among independent experts is treated as evidence of reliability, and multi-round consensus has become a core mechanism o
arXiv:2603.23184v2 Announce Type: replace-cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF), existing reward modeling methods largely rely on explicit feedback,
arXiv:2610.07311v1 Announce Type: new Abstract: Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored
arXiv:2603.16017v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly participate in morally sensitive decision-making, yet how they organize ethical frameworks across re
arXiv:2607.09985v2 Announce Type: replace Abstract: Object pose estimation is a fundamental problem in 3D vision. Although recent state-of-the-art approaches achieve strong performance, generalization
arXiv:2610.07903v1 Announce Type: new Abstract: Adapting vision-language models to downstream tasks has achieved remarkable success by leveraging pseudo-labels generated from unlabeled data. Existing
arXiv:2610.08398v1 Announce Type: new Abstract: On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this i
arXiv:2610.08677v1 Announce Type: new Abstract: Off-policy evaluation (OPE) for contextual bandit policies becomes challenging when action-level importance weighting incurs excessive variance. Doubly
arXiv:2512.13708v2 Announce Type: replace Abstract: Inferring interaction structure from steady-state observations is a central inverse problem when transient trajectories are unavailable. Here we for
arXiv:2610.08402v1 Announce Type: new Abstract: Multi-turn LLM agents often receive sparse task feedback across several interactions, while generating each response token by token. This creates two re
arXiv:2509.26189v2 Announce Type: replace Abstract: The rapid proliferation of Large Language Models has intensified the challenge of distinguishing LLM-generated text from human writing in non-Englis
arXiv:2610.07987v1 Announce Type: cross Abstract: Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense
arXiv:2610.07334v1 Announce Type: new Abstract: Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring kno
arXiv:2610.05281v2 Announce Type: replace Abstract: Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data