PPDL: LLM-Based Flows as Probabilistic Programs
arXiv:2608.05234v1 Announce Type: new Abstract: Building reliable applications that leverage large language models (LLMs) remains a significant challenge. While LLMs offer impressive capabilities acro
Knowledge catalogue
arXiv:2608.05234v1 Announce Type: new Abstract: Building reliable applications that leverage large language models (LLMs) remains a significant challenge. While LLMs offer impressive capabilities acro
arXiv:2511.17241v2 Announce Type: replace Abstract: Understanding and predicting user behavior on social media platforms is crucial for content recommendation and platform design. While existing appro
arXiv:2608.05797v1 Announce Type: cross Abstract: Task difficulty dictates an agent's likelihood of success, and estimating it without rollouts means forecasting this directly from a task description
arXiv:2608.06170v1 Announce Type: cross Abstract: Hierarchical 3D scene graphs are a promising representation for high-level spatial reasoning in autonomous mobile platforms. However, existing extract
arXiv:2608.06240v1 Announce Type: cross Abstract: Unpaired image-to-image translation must decide, per image, what to change and what to preserve without paired supervision. Many diffusion-based unpai
arXiv:2608.05249v1 Announce Type: cross Abstract: Real-world multimodal instructions often bundle multiple requirements with unequal importance, yet most multimodal training data still reduce instruct
arXiv:2608.06015v1 Announce Type: cross Abstract: Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch,
arXiv:2608.05225v1 Announce Type: new Abstract: Research agents can increasingly search literature, propose hypotheses, generate code, run experiments, and draft manuscripts from a single topic. Howev
arXiv:2507.00673v2 Announce Type: replace-cross Abstract: Image segmentation is central to automated medical image analysis, enabling precise identification of anatomical structures and pathological r
arXiv:2608.05686v1 Announce Type: cross Abstract: Quantum error correction protects logical information only when every physical operation remains below the fault-tolerance threshold, a condition that
arXiv:2608.05326v1 Announce Type: cross Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache. A dominant line of work
arXiv:2608.05230v1 Announce Type: cross Abstract: The daily allocation of the finite 24-hour time budget is strongly associated with physical, mental, and cognitive health. While predictive models can
arXiv:2608.06294v1 Announce Type: new Abstract: Cardiac arrest remains one of the most lethal conditions encountered in intensive care units. Despite the growing availability of electronic health reco
arXiv:2608.05371v1 Announce Type: new Abstract: World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing
arXiv:2608.05714v1 Announce Type: new Abstract: Text-to-CAD generation translates natural-language design intent into editable and executable parametric computer-aided design (CAD) codes, reducing the
arXiv:2608.05646v1 Announce Type: cross Abstract: Exact QAOA simulation spans several computational representations whose useful regions differ sharply across graph structure, circuit depth, precision
arXiv:2606.16278v3 Announce Type: replace-cross Abstract: Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect at scale. Editable 3D Ga
arXiv:2608.05660v1 Announce Type: cross Abstract: As language models are increasingly used for tasks that require verifiable reasoning, reliably distinguishing sound reasoning from flawed reasoning ha
arXiv:2608.05315v1 Announce Type: new Abstract: Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs) often require unsupervised domain adaptation (UDA) to generalize across subjects and
arXiv:2608.05466v1 Announce Type: new Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because ea
arXiv:2608.06151v1 Announce Type: cross Abstract: The emergence of conspiracy theories in the wake of major events is a significant societal challenge. Here we test whether conversational dialogues wi
arXiv:2608.05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollou
arXiv:2511.20633v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) policies excel in aligning language, perception, and robot control. However, most VLAs are trained purely by imitation,
arXiv:2608.05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long
arXiv:2608.06353v1 Announce Type: cross Abstract: We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle th
arXiv:2608.05945v1 Announce Type: new Abstract: Test-time adaptation (TTA) can improve the recognition accuracy of vision-language models under distribution shift, but often degrades calibration, maki
arXiv:2608.06211v1 Announce Type: cross Abstract: Significant advancements in deep learning have been made possible by the utilization of large datasets, underscoring the critical importance of copyri
arXiv:2409.06130v2 Announce Type: replace-cross Abstract: Modern machine learning models require substantial computational resources and data to train, making them valuable intellectual property. Mode
arXiv:2608.05154v1 Announce Type: new Abstract: Rotary positional encoding (RoPE) is a core component of modern language models and has been extended to multimodal LLMs through multidimensional varian
arXiv:2608.06221v1 Announce Type: cross Abstract: Learning from demonstration (LfD) provides a developmental framework through which robots can develop motor skills by observing and imitating human dy
arXiv:2608.05430v1 Announce Type: cross Abstract: The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete incr
arXiv:2509.16666v2 Announce Type: replace Abstract: Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual
arXiv:2608.05903v1 Announce Type: new Abstract: Mainstream World-Action Models (WAMs) adapt pretrained video generation models (VGMs) for robot control, transferring their learned dynamics prior for a
arXiv:2608.06171v1 Announce Type: new Abstract: Web agents observe a browser through text, pixels, or both, and the choice is usually fixed once for all tasks. We measure six observation modes across
arXiv:2608.06347v1 Announce Type: new Abstract: Multilingual reasoning transfer is crucial for extending reasoning capabilities of large language models (LLMs) beyond high-resource languages. On-polic
arXiv:2608.06310v1 Announce Type: cross Abstract: Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong
arXiv:2608.05863v1 Announce Type: new Abstract: Modern models no longer keep a plain KV cache: latent caches, learned sparse selectors and recurrent states each carry the model's memory in a different
arXiv:2608.06259v1 Announce Type: new Abstract: Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, l
arXiv:2608.05158v1 Announce Type: new Abstract: In biological evolution, unconstrained mutation can lead to catastrophic outcomes: organisms may evolve enhanced capabilities while losing essential fun
arXiv:2608.05669v1 Announce Type: cross Abstract: Divertor heat-flux analysis is essential for understanding plasma-wall interactions and protecting plasma-facing components in magnetic-confinement fu
arXiv:2608.06179v1 Announce Type: new Abstract: Preference optimisation has proven effective for improving large language models but typically relies on costly human preference annotations. Extending
arXiv:2608.06125v1 Announce Type: new Abstract: Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human prefer
arXiv:2608.05156v1 Announce Type: new Abstract: Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of para
arXiv:2608.06340v1 Announce Type: cross Abstract: Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, th
arXiv:2608.06167v1 Announce Type: new Abstract: We present a schema-based framework for extracting complex, structured information from unstructured text documents using generative AI, followed by aut
arXiv:2608.05627v1 Announce Type: new Abstract: Training-free open-vocabulary segmentation remains limited by a missing inference abstraction. Frozen vision-language features are produced at patch lev
arXiv:2507.03631v4 Announce Type: replace Abstract: Extracting interpretable mathematical models from complex dynamical systems is difficult, especially for chaotic dynamics observed with noisy experi
arXiv:2608.05691v1 Announce Type: new Abstract: Scientific images are essential for communicating experimental observations, quantitative evidence and conceptual knowledge. Unlike natural images, thei
arXiv:2608.05439v1 Announce Type: new Abstract: Translating natural language instructions into machine-interpretable formal specifications enables robots and autonomous systems to plan, reason, and fo
arXiv:2608.05702v1 Announce Type: new Abstract: Scientific machine learning commonly validates models at the level of a subdomain, a benchmark split, or an explanation for one prediction. Yet such loc
arXiv:2608.05588v1 Announce Type: cross Abstract: Lifelong Multi-Agent Path Finding (LMAPF) requires repeatedly planning collision-free paths for agents that continuously receive new goals upon reachi
arXiv:2608.05245v1 Announce Type: new Abstract: Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-e
arXiv:2608.05212v1 Announce Type: new Abstract: Deep search agents tackle challenging questions through long-horizon web interactions, a process that is both complex and fragile: small reasoning error
arXiv:2608.05864v1 Announce Type: new Abstract: Large language models are increasingly applied as autonomous decision-making agents. However, in executive business decisions, existing benchmarks are l
arXiv:2608.05161v1 Announce Type: new Abstract: Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining rema
arXiv:2608.05858v1 Announce Type: new Abstract: Accurate object detection in aerial and satellite imagery is dependent upon the bounding box representation. This is especially true for spatially orien
arXiv:2607.27934v2 Announce Type: replace Abstract: SHACL shapes enable data graph validation, making automatic shape learning essential for knowledge graph applications. We investigate the well-known
arXiv:2608.05710v1 Announce Type: new Abstract: When an AI system is deployed, the individuals who use and or are evaluated by it form beliefs about how the system operates and use those beliefs to st
arXiv:2506.18203v3 Announce Type: replace Abstract: Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are
arXiv:2608.06085v1 Announce Type: new Abstract: Survey-country metadata can improve an LLM's forecast of an individual response when informative, yet the same cue may redirect the forecast when assign