Knowledge catalogue
arXiv:2609.20353v1 Announce Type: new Abstract: We study repeated contract design when a principal observes outcomes but not the actions that generate them. The principal may use any bounded outcome-c
arXiv:2609.19683v1 Announce Type: cross Abstract: The deployment of Vision-Language Models (VLMs) on edge devices is severely bottlenecked by memory bandwidth, necessitating aggressive sub-8-bit quant
arXiv:2609.20181v1 Announce Type: new Abstract: Accurate skin lesion segmentation is crucial for reliable computer-aided dermatological diagnosis, yet existing convolutional and transformer-based mode
arXiv:2609.20178v1 Announce Type: new Abstract: Accurately predicting pedestrian intentions is crucial for ensuring safe and proactive interaction between autonomous vehicles and pedestrians. However,
arXiv:2609.20388v1 Announce Type: cross Abstract: Vision-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to execute long-horizon instructions in unknown environments
arXiv:2609.20323v1 Announce Type: new Abstract: Three-dimensional reconstruction from unorganized point clouds remains a challenging problem in computer vision, geometric modeling, and computer-aided
arXiv:2609.20299v1 Announce Type: new Abstract: Information aggregation across model layers are revealed to improve OOD detection. In contrast to crafting a method for layer-wise information aggregati
arXiv:2609.19210v1 Announce Type: cross Abstract: Graph neural networks are widely used for transductive node classification, with accuracy typically measured on randomly drawn train/validation/test s
arXiv:2609.20454v1 Announce Type: cross Abstract: Accurate optimization of a supervised spectral objective need not produce an accurate population subspace or a better predictive representation. We in
arXiv:2609.19230v1 Announce Type: new Abstract: Ultrasound is the most widely deployed imaging modality worldwide, yet clinical AI remains fragmented into narrow single-task models that fail when devi
arXiv:2609.20816v1 Announce Type: cross Abstract: Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and edi
arXiv:2609.19226v1 Announce Type: cross Abstract: AI-mediated platforms coordinate work through LLM agents acting for different principals. In these workflows, privacy loss can be created before a fin
arXiv:2609.19542v1 Announce Type: new Abstract: Open-vocabulary segmentation enables rich semantic perception for UAVs, but frame-wise predictions can remain temporally inconsistent across repeated ob
arXiv:2609.19441v1 Announce Type: cross Abstract: World action models (WAMs) rely on video-generation backbones, requiring substantial memory and compute for deployment. Post-training quantization red
arXiv:2609.20156v1 Announce Type: cross Abstract: Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, tr
arXiv:2609.19588v1 Announce Type: new Abstract: Mechanical intelligence, loosely defined as the reduction in control burden afforded by a robot's physical form, has become a prominent concept in robot
arXiv:2609.19983v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data, but training and inference on large graphs are often bottl
arXiv:2602.04620v3 Announce Type: replace Abstract: GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approxima
Hey community, Jovan from UkisAI here, We're the team behind Swift Qwen3.8 27B, the Qwen model with token usage and overthinking error improvements Our estimate is that we can make a great improvement
arXiv:2609.19513v1 Announce Type: new Abstract: High-quality pre-training data is a critical bottleneck for educational and STEM-specific language models targeting edge AI and on-device deployment whe
arXiv:2609.19636v1 Announce Type: new Abstract: Reinforcement learning now trains language-model agents that act over dozens of steps in live environments. The gains are large, and they are read as be
arXiv:2609.19156v1 Announce Type: new Abstract: Data-driven fine-tuning is widely adopted to enhance reasoning in Large Language Models (LLMs) due to its simplicity and efficiency. However, mainstream
arXiv:2609.19745v1 Announce Type: new Abstract: Fine-grained visual perception in MLLMs is commonly improved by raising the resolution, but the added visual tokens inflate vision-encoding and language
State and local governments are driven by a shared mission to provide responsive, equitable, and accessible services. However, achieving this goal is often hindered by legacy technical debt, disconnec
arXiv:2609.20530v1 Announce Type: new Abstract: We present Relational BabyLM, a system submission to the BabyLM 2026 challenge that combines two cognitively motivated inductive biases in a single deco
arXiv:2609.19654v1 Announce Type: new Abstract: Travel-planning agents generate itineraries that may become infeasible after acceptance because of flight cancellations, hotel unavailability, or attrac
arXiv:2609.19759v1 Announce Type: new Abstract: The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question
arXiv:2609.19241v1 Announce Type: cross Abstract: Large language models fine-tuned for network intrusion detection emit single-point predictions without statistical validity guarantees. Conformal pred
arXiv:2609.20524v1 Announce Type: cross Abstract: Rigid-body interpenetration frequently occurs in procedurally assembled and generated scenes and must be removed before downstream applications such a
arXiv:2607.18554v2 Announce Type: replace-cross Abstract: Learning local policies for continuous networked systems requires accounting for the effects of decisions beyond each agent's observation neig
arXiv:2609.19644v1 Announce Type: new Abstract: Scientific discovery is defined by the ability to identify the boundaries of existing knowledge and venture into unexplored territory. The ultimate visi
arXiv:2609.19476v1 Announce Type: new Abstract: Generative models are increasingly central to many de novo discovery pipelines, in which designs are generated at scale and filtered through virtual scr
arXiv:2609.20086v1 Announce Type: new Abstract: Long-term multivariate time series plays a significant role in many application areas such as power systems, trading, etc. However, their accurate predi
arXiv:2609.19610v1 Announce Type: new Abstract: Understanding humans over long horizons requires agents to infer not only what people need in the moment, but also how routines form, why they repeat, a
arXiv:2609.19533v1 Announce Type: new Abstract: Simultaneous localization and mapping (SLAM) is one of the services running on an autonomous robot. It is typically run to assist other tasks such as pl
arXiv:2609.19867v1 Announce Type: new Abstract: Joint learning across heterogeneous tasks is often treated as task coupling through feature sharing, distillation, or auxiliary supervision. However, in
arXiv:2609.20194v1 Announce Type: cross Abstract: Triangular membership functions (MFs) are widely used in fuzzy systems because of their interpretability, low parameterization complexity, and strong
arXiv:2609.20091v1 Announce Type: new Abstract: The Antibandwidth and Cyclic Antibandwidth problems are NP-hard graph labeling problems that aim to maximize the minimum (cyclic) distance between label
arXiv:2609.20791v1 Announce Type: new Abstract: Hierarchical planning frameworks combine skills from multiple robot control policies for long-horizon task execution, where determining when to terminat
arXiv:2609.20227v1 Announce Type: new Abstract: Resource-constrained multi-object navigation in vast indoor environments (>2,000ext{ m}^2) poses significant challenges for efficiency and strategic pla
arXiv:2609.20334v1 Announce Type: new Abstract: Traffic regulations are written for human interpretation and therefore rely on shared background knowledge and flexible phrasing, which inherently intro
arXiv:2609.20050v1 Announce Type: cross Abstract: A coding agent halfway through an issue has already read much of what a retriever ranks highest. Relevance is scored per passage, but sufficiency belo
arXiv:2609.20131v1 Announce Type: cross Abstract: Reasoning-based reranking with Large Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly r
arXiv:2609.20290v1 Announce Type: new Abstract: Detecting crop disease early is central to sustainable agriculture and food security under United Nations Sustainable Development Goal 2 (Zero Hunger),
arXiv:2609.19770v1 Announce Type: new Abstract: All-atom structure predictors model diverse molecular interactions, but using their learned structural priors for binder design remains challenging. Her
arXiv:2609.19155v1 Announce Type: new Abstract: In Human-LLM dialogue, follow-up user utterances may implicitly conflict with earlier intents, leading the LLM to misinterpret user needs and generate i
arXiv:2609.19897v1 Announce Type: new Abstract: Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genre
arXiv:2609.20214v1 Announce Type: cross Abstract: Early transformer fault diagnosis is challenged by nonlinear dissolved-gas interactions, overlapping fault signatures, and limited labeled data, while
arXiv:2609.19844v1 Announce Type: cross Abstract: AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable fr
arXiv:2609.19878v1 Announce Type: cross Abstract: Multimodal reasoning requires models to draw on information from multiple modalities throughout the reasoning process. Yet existing methods often conc
arXiv:2609.20089v1 Announce Type: new Abstract: Self-evolving methods reduce the need for human-annotated trajectories by allowing tool-using agents to generate their own training data. Yet existing m
arXiv:2609.19628v1 Announce Type: new Abstract: We present VGGT-GS SLAM, a monocular 3D Gaussian Splatting SLAM system designed for uncalibrated videos. Starting from feed-forward VGGT pose and depth
arXiv:2609.19158v1 Announce Type: new Abstract: Knowledge graphs are usually integrated into question answering by encoding a retrieved subgraph with a graph neural network and fusing it with the lang
arXiv:2609.20423v1 Announce Type: new Abstract: Document parsing converts document images into structured content and requires reliable performance across diverse layouts and acquisition conditions. Y
arXiv:2609.20612v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher
arXiv:2609.20427v1 Announce Type: cross Abstract: Automated pain recognition from facial expression could make continuous welfare assessment practical in sheep, but adoption depends on trust: a stockp
arXiv:2609.19671v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and un
arXiv:2609.19868v1 Announce Type: cross Abstract: Autoregressive language models (ARMs) are constrained by sequential, left-to-right generation, while masked diffusion models (MDMs) enable parallel de
arXiv:2609.20310v1 Announce Type: new Abstract: Human activity traces record individuals' timestamped visits to points of interest and are essential for applications such as mobility prediction and ur
arXiv:2410.05433v3 Announce Type: replace Abstract: This paper introduces 2Fast-2Lamaa, a lidar-inertial state estimation framework for odometry, mapping, and localization. Its first key component is