Knowledge catalogue
arXiv:2609.23974v1 Announce Type: new Abstract: Foundation models are endowing autonomous systems with greater intelligence, enabling a more comprehensive understanding of the environment through visu
arXiv:2609.24186v1 Announce Type: new Abstract: Large language models have achieved remarkable progress on Text-to-SQL through reasoning-enhanced fine-tuning, yet existing approaches predominantly rel
arXiv:2609.23589v1 Announce Type: cross Abstract: Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio repre
arXiv:2609.26205v1 Announce Type: new Abstract: Aligning with the human visual system~(HVS) in perceiving and evaluating the quality of visual signals is a central objective of machine-vision-based vi
arXiv:2609.26667v1 Announce Type: new Abstract: Collaboration topology shapes both the performance and execution cost of LLM-based multi-agent systems. Because tasks differ in complexity and required
arXiv:2609.25518v1 Announce Type: new Abstract: Attributing language model outputs to their internal computations is an open problem in interpretability. Existing methods, which use causal interventio
arXiv:2609.24838v1 Announce Type: new Abstract: Medical agents increasingly combine general reasoning models with specialized clinical tools, yet their capabilities remain largely fixed by what clinic
arXiv:2510.21175v2 Announce Type: replace Abstract: Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range
arXiv:2609.26166v1 Announce Type: cross Abstract: Remote Sensing Change Captioning (RSCC), which aims to generate accurate and detailed linguistic descriptions of ground object variations from bi-temp
arXiv:2609.26103v1 Announce Type: new Abstract: Medical Image Super-Resolution (MISR) aims to enhance spatial resolution without requiring hardware modifications. Although deep learning has yielded pr
arXiv:2602.23607v2 Announce Type: replace Abstract: Developing learning-based autonomy for microrobotic manipulation is difficult because physical trials are slow, variable, and poorly suited to large
arXiv:2609.25757v1 Announce Type: new Abstract: What is the least recurrent memory needed to reproduce a specified expert under partial observability? The instantaneous requirement is the conditional
arXiv:2609.25441v1 Announce Type: new Abstract: Legal argument mining supports passage classification, retrieval, and argument completion. This work introduces an expert-annotated dataset of 42 U.S. f
arXiv:2609.25331v1 Announce Type: new Abstract: Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surv
arXiv:2609.25815v1 Announce Type: new Abstract: Visual attribution methods typically explain predictions using pixels, superpixels, or regular patches. These representations can localize important reg
arXiv:2609.25811v1 Announce Type: new Abstract: Multi-view clustering (MVC) aims to uncover latent cluster structures by exploiting complementary information from multiple views. Despite substantial p
arXiv:2609.25907v1 Announce Type: new Abstract: Visual localization (VL) is a fundamental technology for vision applications such as virtual reality. Recently, a novel VL paradigm, Camera Ray Regressi
New paper! 🫡 We introduce Matryoshka Attribution, a new attribution method which uses gradient descent to find which parts of a neural network are responsible for a behaviour. MAttr is #1 on the Mecha
arXiv:2609.22944v1 Announce Type: cross Abstract: Autonomous AI agents increasingly act across organizational boundaries on behalf of human operators: they invoke third-party services, delegate subtas
arXiv:2609.24757v1 Announce Type: cross Abstract: This paper presents the design, optimization, implementation, and on-board validation of a neural processing unit (NPU) accelerator for real-time vehi
arXiv:2609.26402v1 Announce Type: new Abstract: The discovery of novel inorganic materials drives technological breakthroughs in critical fields such as computing and energy storage. Generative AI has
arXiv:2609.23407v1 Announce Type: cross Abstract: Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for emb
arXiv:2609.26624v1 Announce Type: cross Abstract: Sparse Gaussian processes achieve O(N) inference by replacing the kernel with an appropriate expansion in a fixed basis {phi_j} on the input space. Gi
arXiv:2609.26052v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to conventional Auto-Regressive (AR) Large Language Models (LLM
arXiv:2609.22987v1 Announce Type: new Abstract: Automated operations research (OR) modeling requires LLMs to translate natural-language decision problems into correct mathematical programs. Existing m
arXiv:2609.26249v1 Announce Type: new Abstract: Diffusion language models (dLLMs), such as LLaDA and Dream, have become competitive with autoregressive (AR) LLMs in generation quality while supporting
arXiv:2609.26355v1 Announce Type: new Abstract: Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted mat
arXiv:2609.25630v1 Announce Type: new Abstract: Real-world reinforcement learning (RL) systems still struggle with the demands of contact-rich industrial manipulation, including micrometer-level preci
arXiv:2609.25375v1 Announce Type: new Abstract: Global point-cloud registration remains challenging when limited overlap, repetitive geometry, and sensor noise produce correspondence sets dominated by
arXiv:2609.23023v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) require coordinated choices over network representation, sampling, loss construction, and optimization, while e
arXiv:2609.25538v1 Announce Type: new Abstract: While single-view 3D reconstruction has seen significant progress, extrapolating complex 3D structures from inherently ambiguous 2D observations remains
arXiv:2609.26474v1 Announce Type: cross Abstract: Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattere
arXiv:2609.26425v2 Announce Type: new Abstract: KV cache memory has become a major deployment bottleneck for video generation and world models, which motivates low-bit quantization study for efficienc
Got QFN up and running on our Strix box this past weekend and have been running on it for a few days now. Big thank you/shout out to the Halogen team, it's running fantastic on the Strix, this is clea
arXiv:2609.26069v1 Announce Type: cross Abstract: Simulation-based tutor selection can be unstable when predictively adequate learner models imply different policy rankings. RankCert certifies one of
arXiv:2609.25770v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance on tasks such as visual question answering, yet small image resizes can turn correct answ
arXiv:2607.14109v2 Announce Type: replace Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central
arXiv:2609.25492v1 Announce Type: new Abstract: Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ).
arXiv:2609.26648v1 Announce Type: cross Abstract: Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under chall
arXiv:2609.25636v1 Announce Type: new Abstract: Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker than these numbers suggest. We tra
arXiv:2609.25270v1 Announce Type: new Abstract: Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute visual ground truth, leaving bo
arXiv:2609.25490v1 Announce Type: cross Abstract: Consistent multi-view object segmentation is critical for 3D perception and robotics, yet remains challenging under severe viewpoint and occlusion cha
arXiv:2609.25009v1 Announce Type: new Abstract: Numerically equivalent word problems should yield the same canonical answer whether a quantity is written as a decimal, fraction, percentage, number wor
arXiv:2609.25743v1 Announce Type: new Abstract: Interactive segmentation of 3D medical images supports quantitative analysis of anatomical structures and disease while allowing users to specify and re
arXiv:2609.25503v1 Announce Type: new Abstract: With sparse and event-driven computation, spiking neural networks show great potential for achieving accurate and energy-efficient UAV visual tracking.
arXiv:2609.25576v1 Announce Type: cross Abstract: We study the estimation of a K-dimensional simplex from N i.i.d. points sampled uniformly from its interior; the observations are convex combinations
arXiv:2609.22792v1 Announce Type: cross Abstract: LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model
arXiv:2609.26505v1 Announce Type: new Abstract: Retraining visual perception pipelines in High-Mix, Low-Volume (HMLV) automotive manufacturing must be carried out under tight annotation, energy, and t
arXiv:2603.03806v2 Announce Type: replace Abstract: The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting considerable attention for its efficient han
arXiv:2609.25831v1 Announce Type: new Abstract: Recent VLM-based autonomous driving planners adopt GRPO-style reinforcement learning to optimize driving performance. However, existing GRPO recipes eit
arXiv:2609.26780v1 Announce Type: new Abstract: Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish
arXiv:2609.26064v1 Announce Type: new Abstract: Remote sensing object detection (RSOD) requires compact backbones capable of preserving weak geometric cues under extreme scale variation and background
arXiv:2609.26165v1 Announce Type: new Abstract: Weight-space structure often correlates with language-model behavior, but correlation alone does not establish computational involvement. We study conce
arXiv:2609.26488v1 Announce Type: new Abstract: While Chain-of-Thought (CoT) reasoning has improved the capability of language models, directly applying it to Spoken Language Models (SLMs) may introdu
What it is. stuntd is a local proxy for typed LLM decisions: choice, yes/no, score. Your app keeps calling its provider through it. stuntd records the decisions, trains a small head on top of Laya (th
arXiv:2609.25546v1 Announce Type: cross Abstract: Music creation often involves iterative refinement, changing selected musical details while retaining the rest. To support such refinement, we introdu
arXiv:2609.24025v1 Announce Type: new Abstract: We present a method for synthesizing reactive character behaviors for continuous games as compact, human-readable programs. Game AI practice still relie
arXiv:2609.23889v1 Announce Type: cross Abstract: Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and ef
arXiv:2609.26143v1 Announce Type: cross Abstract: Recommender systems on Web platforms tend to over-serve popular items and neglect the long tail. Item-side knowledge graphs (KGs), often available as
arXiv:2609.24243v1 Announce Type: new Abstract: Reinforcement learning (RL) improves reasoning in vision-language models (VLMs) but can induce chain-of-thought (CoT) obfuscation: an operational, non-i