Knowledge catalogue
arXiv:2609.36452v1 Announce Type: cross Abstract: Masked diffusion language models (MDLMs) can generate text efficiently by predicting multiple masked tokens in parallel, but predictions from the same
arXiv:2609.32490v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MASs) have shown strong potential for solving complex tasks, but most assume that task requirements are sufficiently
arXiv:2609.37500v1 Announce Type: new Abstract: On-policy distillation (OPD) trains language models using dense token-level teacher supervision on student-generated trajectories. However, its reliance
arXiv:2609.37916v1 Announce Type: cross Abstract: Production machine learning (ML) stacks often split graph compilation and kernel execution across different layers and languages, making backend behav
arXiv:2609.38072v1 Announce Type: new Abstract: Ultra-high-resolution (UHR) remote sensing visual question answering (VQA) requires models to resolve small visual evidence within extremely large image
arXiv:2609.36601v1 Announce Type: new Abstract: On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teac
arXiv:2609.36918v1 Announce Type: new Abstract: Part-level 3D assets are essential for editing, reassembly, and interaction, yet recovering such structure from a single image remains challenging due t
arXiv:2609.37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing app
Hey guys - half a tutorial/guide, and half an I built this, so I went for resources. This is something that I created for myself recently when I couldn't find any good existing solution. I wrote this
arXiv:2609.37172v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuris
arXiv:2609.38178v1 Announce Type: cross Abstract: Robots deployed in the physical world must be able to improve beyond their initial training as they encounter new situations and failures. For this im
arXiv:2609.37128v1 Announce Type: new Abstract: Skill evolution improves the capabilities of large language models by analyzing trajectories generated under a given skill and modifying the skill accor
arXiv:2609.37539v1 Announce Type: new Abstract: Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in
arXiv:2609.36879v1 Announce Type: cross Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent S
arXiv:2609.37626v1 Announce Type: cross Abstract: No single way of parallelizing attention serves large language models well under all loads. Low concurrency favors tensor parallelism, many independen
arXiv:2609.36900v1 Announce Type: new Abstract: Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training score
arXiv:2609.36720v1 Announce Type: new Abstract: Memory-dependent robotic manipulation requires policies to use information that is no longer available in the current observation. Retaining history alo
arXiv:2609.35810v1 Announce Type: cross Abstract: Large language models are increasingly used in oncology applications, but their predictions are often weakly grounded in explicit medical structure. W
arXiv:2609.37132v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves large language models by letting a self-teacher with privileged information provide dense token-level superv
arXiv:2512.18991v3 Announce Type: replace-cross Abstract: Dominant paradigms for 4D LiDAR panoptic segmentation are usually required to train deep neural networks with large superimposed point clouds
arXiv:2603.28773v2 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon oft
Apple Foundation Model 3 through Private Cloud Compute is directly available in macOS 27.2 through familiar AI clients. For Mac users running local models such as Qwen 3.x or Gemma 4, AFM 3 PCC is a c
arXiv:2609.37098v1 Announce Type: cross Abstract: Vehicle-infrastructure cooperation can complement onboard sensing with broader and more informative observations of the traffic environment, providing
arXiv:2609.36804v1 Announce Type: cross Abstract: Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and gramma
arXiv:2609.36572v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further en
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact
arXiv:2609.37922v1 Announce Type: new Abstract: Visual Language Action (VLA) models offer unprecedented generalization for autonomous robots; however, their real-world deployment is frequently bottlen
arXiv:2609.36398v1 Announce Type: cross Abstract: Generative models make molecular crystal structure prediction fast, but their samples still exhibit geometric and packing violations. Physics can be i
arXiv:2609.38121v1 Announce Type: new Abstract: KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck,
arXiv:2609.37902v1 Announce Type: new Abstract: Existing LLM routers choose among models using static per-model costs. We show that open-weight inference markets introduce a second, largely ignored de
I wanted a fun way to visualize and stress-test a multi-agent ecosystem, so I pointed it at my favorite MMO (a vanilla-era private server emulator). Live view: https://design.kristiantalley.com/projec
arXiv:2607.14522v2 Announce Type: replace Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control
arXiv:2609.34547v1 Announce Type: new Abstract: Video-capable vision-language models score above 80% on popular benchmarks yet struggle with spatial-temporal binding: associating the right action with
arXiv:2609.32976v1 Announce Type: new Abstract: Incorrect or corrupted labels in tabular datasets can significantly degrade supervised learning performance, particularly when mislabeling is subtle and
arXiv:2609.34034v1 Announce Type: cross Abstract: A central aim of neuromorphic computing is to provide a viable alternative to highly energy-intensive Transformer-based AI. However, efficient alterna
arXiv:2609.35090v1 Announce Type: new Abstract: Video-text pretraining has achieved remarkable progress through the scaling of models and datasets, yet the quality of language supervision remains unde
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
'Agent security will be solved in the open, collaboratively, together.' At Red Hat, open is the mission, so couldn't agree more. Red Hat has been part of the OpenShell project from the early days, as
arXiv:2609.34683v1 Announce Type: new Abstract: The optimization of LLM serving engines, such as vLLM and SGLang, is largely benchmark-driven: optimizations, scheduling policies, hardware and system d
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:2609.32762v1 Announce Type: cross Abstract: Visual imitation learning is a promising approach to training robot manipulation policies capable of completing a wide variety of tasks. However, poli
arXiv:2604.07666v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used for post-training Large Language Models, but practical verifiers can make error
arXiv:2609.32740v1 Announce Type: new Abstract: Intraoperative anesthesia requires systems to interpret evolving multimodal evidence, recommend timely management, and revise decisions as patient state
arXiv:2609.32156v1 Announce Type: cross Abstract: Safe underwater exploration requires a robot to understand where surrounding structures are located and which regions are available for motion. Existi
arXiv:2609.33662v1 Announce Type: cross Abstract: Imperfect verifiers can assign a harmful update direction even when clipping and regularization bound its magnitude. We introduce Audit-First VAPO, wh
arXiv:2510.10902v3 Announce Type: replace Abstract: Auditing information disclosure across every datapoint during the training of LLMs is challenging. We propose a principled, attack-agnostic approach
arXiv:2609.34270v1 Announce Type: new Abstract: Interactive robot planning requires robots to infer and execute human intentions from natural language instructions that are often ambiguous, incomplete
arXiv:2609.34145v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) gives vision--language driving systems access to external safety knowledge, yet a retrieved risk rule may be releva
arXiv:2609.31957v1 Announce Type: new Abstract: Interactive CAPTCHAs remain challenging for computer-use agents, while existing datasets face trade-offs among type coverage, interaction fidelity, and
arXiv:2609.33147v1 Announce Type: new Abstract: Federated low-rank adaptation (LoRA) enables collaborative fine-tuning of large language models without centralizing private client data. Its factorized
arXiv:2609.35462v1 Announce Type: new Abstract: Patients often have several co-occurring clinical conditions, and the findings needed to identify and disambiguate them emerge over the course of a cons
arXiv:2609.35476v1 Announce Type: new Abstract: Embodied co-painting requires a robot to repeatedly update a shared physical canvas while human intent evolves over interaction. Existing reference-driv
arXiv:2609.34992v1 Announce Type: new Abstract: Decoding for large language models is typically treated as a collection of isolated sampling strategies, with limited theoretical understanding of the b
arXiv:2603.08309v3 Announce Type: replace Abstract: Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than
arXiv:2609.34196v1 Announce Type: new Abstract: Modern vision-language models (VLMs) achieve strong performance across a broad range of multimodal tasks, yet still struggle with visual questions that
arXiv:2609.32781v1 Announce Type: new Abstract: Diffusion vision-language models generate answers by gradually resolving masked tokens, making accurate conditional prediction in partially resolved sta
arXiv:2609.31873v1 Announce Type: new Abstract: Keyframe selection (KFS) has long produced compact video summaries for browsing and retrieval, and representative frames for thumbnails. More recently,
arXiv:2609.33878v1 Announce Type: cross Abstract: Merchant matching resolves a noisy payment descriptor to a retrieved merchant entity or returns no match. A key challenge in curating training labels
Over the last three decades in cybersecurity, I’ve witnessed major paradigm shifts — yet none match the velocity and complexity of today’s landscape. Attackers are now using AI to move at machine spee
arXiv:2609.33836v1 Announce Type: cross Abstract: Construction environments evolve continuously, causing large geometric changes that degrade static mapping and registration performance. This necessit