Knowledge catalogue
arXiv:2607.26809v1 Announce Type: new Abstract: General-purpose robotic manipulation requires robots to perform diverse tasks in open-world environments while improving their skills over time. Despite
arXiv:2607.26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning
arXiv:2607.26627v1 Announce Type: new Abstract: Speculative Decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose tokens that are subsequently verif
arXiv:2607.26885v1 Announce Type: new Abstract: Vision-language pre-training (VLP) serves as a cornerstone for medical multimodal representation learning. However, existing medical VLP frameworks are
arXiv:2607.26670v1 Announce Type: cross Abstract: The rapid growth of scholarly literature has made identifying relevant publications increasingly difficult, and conventional search systems still depe
arXiv:2603.18271v3 Announce Type: replace Abstract: Ambiguity poses a major challenge to large language models (LLMs) used as robotic planners. In this letter, we present Scene Graph-Chain-of-Thought
arXiv:2607.26173v1 Announce Type: new Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised
arXiv:2607.26595v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing dem
arXiv:2504.17901v3 Announce Type: replace Abstract: Task and motion planning (TAMP) is a well-established approach for solving long-horizon robot planning problems. Although TAMP methods have historic
arXiv:2607.26536v1 Announce Type: new Abstract: High-pressure prompts can push vision-language models (VLMs) into unsupported commitments, such as reading illegible text, reporting indeterminate times
arXiv:2510.00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational
arXiv:2607.26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm
arXiv:2607.26795v1 Announce Type: new Abstract: Span-guided rewriting aims to preserve meaning by localizing edits to annotated harmful spans, but the same constraint can leave harmful intent insuffic
arXiv:2607.25202v1 Announce Type: new Abstract: Conversational entrainment is well-studied in monolingual and written contexts, but remains underexplored in spoken code-switching (CSW). We present a n
arXiv:2605.05580v2 Announce Type: replace Abstract: Quantitative trading agents have demonstrated substantial promise in automating factor discovery, signal aggregation, and portfolio execution. Howev
arXiv:2607.24774v1 Announce Type: new Abstract: Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only grown si
arXiv:2607.24984v1 Announce Type: cross Abstract: In recent years, the number of events in earthquake catalogs has significantly increased due to the utilization of more effective deep learning based
BREAKING: Grok 4.5 just claimed the top spot on the new HighWalk Benchmark. The independent test measures how well AI models update real technical specifications from 46 Laravel commits — heavy on cod
arXiv:2607.25929v1 Announce Type: cross Abstract: Deep generative models (DGMs) are widely used for complex high-dimensional data and increasingly applied to spatial and spatio-temporal modeling. Thei
arXiv:2607.25340v1 Announce Type: new Abstract: The same episode of atrial fibrillation is a minor finding in a healthy adult and grounds for anticoagulation in an elderly patient with hypertension: i
arXiv:2607.25294v1 Announce Type: cross Abstract: Real-world tasks often require models to learn from task-specific context rather than relying only on pre-trained knowledge. While recent work has hig
arXiv:2607.25018v1 Announce Type: new Abstract: Large language model (LLM) cascades reduce inference cost by routing easy queries to a small model and deferring hard queries to a larger one. Productio
arXiv:2607.25959v1 Announce Type: cross Abstract: Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation. Their knowledge is deeply connect
arXiv:2408.03291v4 Announce Type: replace Abstract: Vision Transformers (ViTs) have gained significant attention, but their high computing cost limits the practical applications. While post-training q
arXiv:2607.25335v1 Announce Type: cross Abstract: Prompt compression shortens LLM input to reduce inference cost, yet existing methods score token importance through LM forward passes. It remains ques
arXiv:2607.21859v2 Announce Type: replace Abstract: Constructing causal directed acyclic graphs (DAGs) is a core step in biomedical causal analysis, yet it remains a largely manual process. Analysts m
arXiv:2607.24847v1 Announce Type: cross Abstract: We introduce an extremal invariant associated with Chowla-type order conditions in finite groups. A nonempty subset S of a finite group G is called a
arXiv:2607.24889v1 Announce Type: cross Abstract: Financial models combine public disclosures with analyst assumptions to produce forecasts and valuations. While some components can be checked mechani
arXiv:2607.24779v1 Announce Type: new Abstract: Online advertising bidding systems typically deploy multiple offline-trained expert models (e.g., PID controllers, model predictive control, offline RL
arXiv:2303.13102v2 Announce Type: replace Abstract: Existing Optimal Transport (OT) methods mainly derive the optimal transport plan/matching under the criterion of transport cost/distance minimizatio
arXiv:2607.25125v1 Announce Type: new Abstract: Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. Wh
arXiv:2602.10282v2 Announce Type: replace Abstract: Large language models (LLMs) have shown potential in identifying qualitative causal relations, but their ability to perform quantitative causal reas
arXiv:2607.24892v1 Announce Type: cross Abstract: Text-conditioned time-series forecasting predicts a series from both its numerical history and natural-language context, allowing forecasts to account
arXiv:2607.24769v1 Announce Type: new Abstract: With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-risk deployment settings. While recent work has emp
arXiv:2607.25663v1 Announce Type: new Abstract: Transformer adaptation is typically distributed across model depth, even when the intended change is narrow. We investigate how adaptation site shapes w
arXiv:2607.25420v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in recommender systems, but it is often unclear how much performance can be obtained from strong pr
arXiv:2607.25090v1 Announce Type: new Abstract: Machine learning engineering (MLE) tasks require long-horizon decision making over iterative solution debugging and refinement, under expensive and feed
arXiv:2607.24765v1 Announce Type: cross Abstract: Large language models (LLMs) can give different answers to the same decision problem across runs, and reverse a decision when their own prior answer r
arXiv:2603.27176v2 Announce Type: replace Abstract: Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language
Model + harness. We have barely begun to understand the best ways to do harness engineering. A huge amount of untapped potential even without models getting better (but models are getting better) Turn
arXiv:2607.25865v1 Announce Type: cross Abstract: Quantum error correction (QEC) is indispensable for scalable fault-tolerant quantum computing. However, discovering QEC codes that remain effective is
arXiv:2508.00344v5 Announce Type: replace Abstract: Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces chall
arXiv:2607.18060v2 Announce Type: replace Abstract: Long-horizon robotic tasks require diverse capabilities that no single policy can reliably provide. Heterogeneous policies offer complementary stren
arXiv:2606.13040v2 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These r
arXiv:2607.25135v1 Announce Type: new Abstract: Recent advances in RAG aim to optimize for performance by paying high ingestion costs for knowledge ingestion: building knowledge graphs or extracting S
arXiv:2607.25388v1 Announce Type: new Abstract: Autonomous multi-vehicle racing requires real-time planning of diverse competitive behaviors in intense interactions. Existing planners often struggle t
arXiv:2607.25026v1 Announce Type: cross Abstract: In this work, we present a simulation-based parameter estimation framework for a model defined by a computational simulation of a physical system. We
arXiv:2607.25305v1 Announce Type: new Abstract: Macroareas are geographical areas used in typological research for grouping variables of interest. In linguistic typology, languages in a given macroare
arXiv:2607.25393v1 Announce Type: new Abstract: Histopathological examination primarily relies on hematoxylin and eosin (H&E) and immunohistochemistry (IHC) staining. Although IHC provides critical mo
Hi. Many people think uncensored models are basically the same model that just doesn't refuse, but... I was recently checking whether uncensored models would give me better answers for stock market pr
Everyone is talking about Kimi K3, but if you jump straight into the technical report, you’ll quickly realize it’s standing on years of research -- just like any breakthrough is! If you want to unders
arXiv:2607.24783v1 Announce Type: new Abstract: Job understanding is critical to LinkedIn's mission of connecting talent with opportunity. This task involves transforming unstructured and noisy job po
arXiv:2607.14137v2 Announce Type: cross Abstract: To answer a question about a program, move the program to where the question is decidable. Every such move is a translation, and every translation is
arXiv:2607.24748v1 Announce Type: cross Abstract: Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing t
We hope these experiments serve as a reminder that evals rarely measure models in isolation—they also measure a bundle of less visible choices about API settings, harness design, and prompting. If you
arXiv:2607.23633v1 Announce Type: cross Abstract: Sky-image irradiance studies often compare forecasting systems in which the image encoder, temporal model, fusion block, target definition, and traini
arXiv:2607.22598v1 Announce Type: cross Abstract: Educational chatbots powered by large language models (LLMs) show promising effects on learning outcomes, yet most systems delegate pedagogical decisi
arXiv:2607.23784v1 Announce Type: cross Abstract: While vision-language-action models have demonstrated impressive zero-shot manipulation capabilities, they remain fundamentally black box policies tha
arXiv:2607.23183v1 Announce Type: cross Abstract: Neurological disorders are a leading cause of global disability and are increasingly linked to environmental chemical exposures. Yet neurotoxicity ass
arXiv:2607.24162v1 Announce Type: new Abstract: Optimizing agentic workflows, such as retrieval-augmented generation (RAG) pipelines, requires navigating a combinatorial space of discrete component ch