Knowledge catalogue
arXiv:2603.20475v3 Announce Type: replace Abstract: Standard attribution heatmaps show where a vision-language model (VLM) focuses, but they do not reveal whether the recovered evidence is organized b
arXiv:2409.06679v3 Announce Type: replace Abstract: Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and documen
arXiv:2604.12013v1 Announce Type: new Abstract: Modern large language models generate text autoregressively, producing tokens one at a time. To study the learnability of such systems, Joshi et al. (CO
arXiv:2604.10658v1 Announce Type: new Abstract: Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpos
arXiv:2604.08712v1 Announce Type: new Abstract: The generation of planning domains from natural language descriptions remains an open problem even with the advent of large language models and reasonin
arXiv:2610.21347v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly operate in multi-turn interactions that require maintaining latent conversational states, not only explicit fa
arXiv:2610.21573v1 Announce Type: new Abstract: Decision trees can make vision-language model (VLM) classification interpretable by replacing a single prediction with a sequence of root-to-leaf questi
arXiv:2610.21308v1 Announce Type: cross Abstract: Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text ra
arXiv:2606.09449v2 Announce Type: replace Abstract: Autoformalization (AF) requires both prover acceptance and fidelity to an informal source, but prover acceptance alone cannot establish fidelity, an
arXiv:2610.22324v1 Announce Type: new Abstract: One of the first steps of a research pipeline is generating ideas. Large Language Models (LLMs) are increasingly used to automate this step, but most of
arXiv:2610.21159v1 Announce Type: new Abstract: On-screen text can describe what a video shows, or it can frame what the video is supposed to mean. Current benchmarks treat both alike, testing whether
arXiv:2610.21397v1 Announce Type: new Abstract: An AI data center is committed years before it draws a watt: a few discrete choices (grid or on-site gas, evaporative or dry cooling, which county to fi
arXiv:2402.03164v3 Announce Type: replace Abstract: Representing time is crucial for cyber-physical systems and has been studied extensively in the situation calculus. The most commonly used approach
arXiv:2610.17869v1 Announce Type: new Abstract: Multi-agent Large Language Model (LLM) systems typically commit to a deliberation protocol before inference. A fixed protocol cannot allocate computatio
arXiv:2610.17734v1 Announce Type: new Abstract: Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent samp
arXiv:2610.11289v1 Announce Type: new Abstract: Autonomous scientific discovery with LLMs requires generating and testing hypotheses adaptively as evidence accumulates while maintaining statistical va
arXiv:2610.08660v1 Announce Type: new Abstract: Background: Biomedical AI can generate plausible explanations without reliably verifying whether each statement is supported by patient-specific evidenc
arXiv:2610.07269v1 Announce Type: new Abstract: Cross-view geo-localization is commonly solved as an image retrieval problem, matching a ground-level image against a database of satellite tiles throug
arXiv:2610.04351v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) increasingly aggregates multi-view evidence with heavy learned 3D networks. We propose LoCoSplat (Local-Contex
arXiv:2610.03622v1 Announce Type: new Abstract: The construction industry faces persistent labor shortages, low productivity that costs the global economy over $1.6 trillion annually, and one of the h
arXiv:2610.00296v1 Announce Type: cross Abstract: Token-level certainty is widely used as a proxy for correctness in LLM training and inference. However, the performance of certainty-based methods dep
arXiv:2609.37915v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) trains a student to match a privileged teacher distribution along its own sampled trajectory. Standard OPSD applies
arXiv:2609.30897v1 Announce Type: new Abstract: How should we evaluate language models when more than one interpretation can be right? Cultural benchmarks often test factual knowledge, agreement with
This keeps happening and has been happening for over a month now. Since ollama has zero support I'm hoping someone else has figured out a work around for the issue. I'm using the latest version of ope
arXiv:2609.27833v1 Announce Type: new Abstract: Many computations admit several valid execution orders because independent subgoals or disjoint state updates can commute. Reinforcement learning with v
arXiv:2609.28437v1 Announce Type: new Abstract: Online information is increasingly consumed in video format. Much of this comes in the form of *raw video*: continuous footage taken on a cell phone, wi
arXiv:2609.27346v1 Announce Type: new Abstract: Reliable localization of non-line-of-sight (NLOS) pedestrians is critical for safe urban autonomous driving, yet it remains highly challenging in ego-dy
arXiv:2609.22939v1 Announce Type: cross Abstract: Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for
arXiv:2509.00754v3 Announce Type: replace Abstract: Dempster--Shafer theory (DST) provides an attractive framework for multi-source information fusion. However, its effectiveness critically depends on
arXiv:2609.21486v1 Announce Type: new Abstract: Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene repr
arXiv:2609.20825v1 Announce Type: new Abstract: Clinical predictive models often rely on structured Electronic Health Record data, such as time-series and procedure codes. While recent approaches have
arXiv:2609.21165v1 Announce Type: new Abstract: Off-target protein binding is a major source of adverse effects for small-molecule drugs, yet most structure-based molecular design methods focus on gen
arXiv:2609.19527v1 Announce Type: cross Abstract: Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate.
arXiv:2609.19803v1 Announce Type: new Abstract: Multi-agent heterogeneous air-ground robot teams are attractive for open world search, with applications for reconnaissance, urban search and rescue mis
arXiv:2602.15868v3 Announce Type: replace Abstract: Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic m
arXiv:2609.16091v1 Announce Type: new Abstract: Tabular foundation models deliver strong zero-training predictive performance via in-context learning, but their high inference latency makes them impra
AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills acr
arXiv:2609.12105v1 Announce Type: cross Abstract: The prevailing assumption in applied machine learning is that progress on consequential quantitative decisions such as pricing risk, allocating capita
arXiv:2607.17213v2 Announce Type: replace Abstract: Building long-horizon robot agents requires composing closed-loop pipelines -- perception, belief update, planning, and control -- whose components
Same 44-token prompt: low = 202 output tokens in 15s, max = 4,955 in 35s, unset = 10,579 in 68s. I'm using it via claude code with this: CLAUDE_CODE_MAX_CONTEXT_TOKENS=1048576 ollama launch claude --m
arXiv:2609.10831v1 Announce Type: cross Abstract: Longitudinal single cell atlases now capture matched pre treatment and post treatment states from responders and non responders, presenting an opportu
arXiv:2609.09184v1 Announce Type: new Abstract: Vision-language model (VLM) confidence may change in aggregate when visual evidence is degraded while remaining structurally inconsistent within individ
arXiv:2609.06226v1 Announce Type: cross Abstract: Large language models (LLMs) have recently made substantial progress in formal proof generation, yet presenting distinctive challenges in cryptographi
arXiv:2609.08316v1 Announce Type: new Abstract: Multi-modal large language models (MLLMs) have demonstrated significant potential in image quality assessment (IQA) by bridging visual perception with d
arXiv:2609.05880v1 Announce Type: new Abstract: Piping and Instrumentation Diagrams (P&IDs) are the authoritative maps of process plants: isolation, maintenance, and HAZOP decisions depend on what con
arXiv:2609.03526v1 Announce Type: new Abstract: Multimodal language models achieve near-ceiling scores on food recognition benchmarks, yet it remains unclear whether this success reflects genuine cult
arXiv:2609.00658v1 Announce Type: new Abstract: Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Ye
Hello! I've just uploaded a recent checkpoint of my model trained from scratch: https://huggingface.co/piotr-ai/polanka_3.7b_exp_wip_260901 It was pre-trained, mid-trained, and fine-tuned on a single
arXiv:2608.26602v1 Announce Type: cross Abstract: Large software repositories are often beyond model context limits. Training repository knowledge into models is costly and quickly stale, while local
arXiv:2608.26809v1 Announce Type: new Abstract: While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or short video clips. Editing long videos
arXiv:2608.21418v1 Announce Type: new Abstract: Manufacturing knowledge graphs that integrate data from heterogeneous industrial systems face a trust deficit: consumers cannot determine whether querie
arXiv:2608.23065v1 Announce Type: cross Abstract: Cultural understanding in video means more than recognizing what is visible; it requires grasping the symbolic and temporal significance of cultural c
arXiv:2608.21438v1 Announce Type: new Abstract: Text guided 3D scene editing provides an intuitive interface for modifying reconstructed environments, but remains difficult because natural language de
arXiv:2608.21832v1 Announce Type: new Abstract: Computer-use agents ground natural-language instructions in screenshots to locate interface elements, yet existing benchmarks do not isolate whether mod
arXiv:2608.22337v1 Announce Type: cross Abstract: Speech-guided referring video object segmentation aims to recover the mask tracks of objects specified by a spoken motion description. Here, speech ca
arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video an
arXiv:2608.20348v1 Announce Type: cross Abstract: Electronic health records now routinely exceed 100,000 tokens per patient. Yet large language models exhibit the lost-in-the-middle (LitM) effect: inf
arXiv:2608.20345v1 Announce Type: cross Abstract: Conversational AI systems have become informal mental health support resources for Generation Alpha (Gen Alpha, born 2010-2024), with 13.1% of U.S. ad
arXiv:2608.19701v1 Announce Type: new Abstract: Long-term multi-agent systems continuously accumulate the memories produced by different agents. Existing memory methods typically treat retrieved memor
arXiv:2608.19009v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof ass