Knowledge catalogue
arXiv:2609.39740v1 Announce Type: new Abstract: Long-context reasoning faces two complementary bottlenecks: retaining evidence across long inputs and sustaining computation across many reasoning steps
arXiv:2609.39125v1 Announce Type: new Abstract: Visual-inertial odometry (VIO) for aerial robots relies on high rate inertial measurement unit (IMU) propagation between visual updates. However, conven
arXiv:2609.39938v1 Announce Type: cross Abstract: Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, wherea
arXiv:2603.06281v3 Announce Type: replace Abstract: Generative zero-shot learning (ZSL) synthesizes visual features for unseen classes by learning a semantic-conditioned generator from seen classes. S
arXiv:2609.40219v1 Announce Type: cross Abstract: World Action Models (WAMs) couple visual dynamics prediction with action generation, yet they do not explicitly support the reuse of action experience
arXiv:2602.23934v2 Announce Type: replace-cross Abstract: This paper presents a novel autonomous robotic assembly framework for constructing stable structures without relying on predefined architectur
arXiv:2609.39953v1 Announce Type: new Abstract: Omni-modal large language models (OmniLLMs) enable unified audio-video understanding, but their long multimodal token sequences make deployment computat
arXiv:2609.38743v1 Announce Type: new Abstract: LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retriev
arXiv:2609.39527v1 Announce Type: new Abstract: The presence of lens flares in images can significantly reduce the quality of downstream application results for tasks such as 3D scene reconstruction.
arXiv:2604.08454v2 Announce Type: replace Abstract: Large language models are increasingly deployed in high-stakes domains, where confident yet incorrect inferences may cause severe real-world harm, b
arXiv:2609.40055v1 Announce Type: cross Abstract: On-policy distillation (OPD) provides dense supervision directly on student-generated trajectories, making it an effective post-training strategy for
arXiv:2609.39507v1 Announce Type: new Abstract: General-purpose agents can plan, use tools, and revise their behavior from feedback, but it remains unclear whether these capabilities transfer from dig
arXiv:2609.40222v1 Announce Type: new Abstract: When a camera revisits a previously observed region, a video world model should reproduce what was there before. This requires both remembering past obs
arXiv:2609.40079v1 Announce Type: cross Abstract: While recent Multimodal Large Language Models (MLLMs) have shown promise in affective computing, their reasoning capabilities are largely confined to
arXiv:2609.38955v1 Announce Type: cross Abstract: Inverse Reinforcement Learning (IRL) aims to recover a reward function that explains expert demonstrations. Existing IRL methods typically rely on a b
arXiv:2609.40305v1 Announce Type: new Abstract: Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternati
arXiv:2609.38426v1 Announce Type: cross Abstract: We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL combines Module-Loop and Model-L
arXiv:2602.03537v2 Announce Type: replace Abstract: Matryoshka Quantization (MatQuant), Any-Precision-LLM (AP) and AnyBCQ (AB) are recent quantization approaches showing that a single integer-quantize
arXiv:2609.39920v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) exhibit strong multimodal in-context learning (ICL) capabilities, yet this ability degrades substantially as mode
arXiv:2609.38718v1 Announce Type: new Abstract: Steering large language models typically relies on linear, context-independent interventions in activation space, an assumption that recent work has cha
arXiv:2609.39982v1 Announce Type: cross Abstract: Terminal agents act through stochastic model generations, yet the ability to generate a useful action does not ensure its reliable execution. A poor c
arXiv:2609.39628v1 Announce Type: new Abstract: This paper proposes MIND, a marginal-invariant neural dependency diffusion model for mixed-type tabular data. MIND does not directly learn the joint dis
arXiv:2609.38979v1 Announce Type: new Abstract: Multiple object hallucination, where large vision-language models (LVLMs) generate objects not supported by the visual input, is a persistent challenge
arXiv:2609.38428v1 Announce Type: new Abstract: Real-time commentary for Multiplayer Online Battle Arena (MOBA) esports requires a vision-language model (VLM) to narrate a live match second by second,
arXiv:2609.38294v1 Announce Type: new Abstract: We study the generation of agentic workflows that jointly optimize multiple objectives, such as accuracy, cost, latency, robustness, and consistency. Ex
arXiv:2609.38324v1 Announce Type: cross Abstract: Multi-agent systems of LLMs add discussion to majority voting and are therefore expected to be more capable. However, empirical reports conflict on wh
arXiv:2609.39076v1 Announce Type: new Abstract: A pool of language models can collaborate and improve collectively by learning from one another's responses. These interactions depend on the instructio
arXiv:2609.38587v1 Announce Type: new Abstract: Electroencephalography (EEG) is recorded continuously over hours, with relevant dynamics spanning timescales from milliseconds to hours. Most EEG founda
arXiv:2609.39594v1 Announce Type: new Abstract: As robots are increasingly deployed in everyday environments, ensuring their safety has become a central challenge. Existing methods often encode safety
arXiv:2609.39000v1 Announce Type: new Abstract: Whole-body teleoperation requires a humanoid robot to reproduce a human operator's behavior even when their terrains differ. This demands that the robot
arXiv:2609.38691v1 Announce Type: new Abstract: Streaming video generators allow users to dynamically modulate video synthesis via mid-stream prompt switching. Existing streaming methods can respond t
arXiv:2609.39346v1 Announce Type: new Abstract: Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (SL
arXiv:2601.20701v2 Announce Type: replace Abstract: Real-time robot control demands fast action generation. Diffusion and flow matching policies for robot control require multi-step sampling, limiting
arXiv:2609.38930v1 Announce Type: cross Abstract: In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving alignment with evaluation m
arXiv:2609.38345v1 Announce Type: cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically as
arXiv:2609.40265v1 Announce Type: new Abstract: Real-world time-series applications increasingly require models that can handle time series forecasting, context-conditioned prediction, and language-ba
arXiv:2609.39884v1 Announce Type: cross Abstract: Role prompting elicits specialized behavior from large language models through an expert identity, offering a lightweight way to guide reasoning on de
arXiv:2609.34284v2 Announce Type: replace Abstract: Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its appli
arXiv:2604.02543v2 Announce Type: replace Abstract: As vision-language models (VLMs) are increasingly deployed in clinical decision support, more than accuracy is required: knowing when to trust their
arXiv:2609.38482v1 Announce Type: cross Abstract: Existing architectures for LLM-based multi-agent systems (MAS) cannot reliably and efficiently solve multi-step tasks at scale: they struggle to suppo
arXiv:2609.39880v1 Announce Type: cross Abstract: Passwords remain the dominant online authentication mechanism, and understanding how humans choose them is essential for defensive strength estimation
arXiv:2609.39329v1 Announce Type: new Abstract: Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compressio
arXiv:2609.39427v1 Announce Type: new Abstract: Detecting missing components on printed circuit boards (PCBs) differs fundamentally from conventional object detection, as the model must localize compo
arXiv:2609.38490v1 Announce Type: cross Abstract: Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to und
arXiv:2609.40358v1 Announce Type: new Abstract: Video world models are expected to predict how the physical world evolves, yet they often produce visually plausible videos that violate basic physical
arXiv:2602.08277v3 Announce Type: replace-cross Abstract: The landscape of AI video generation is undergoing a pivotal shift: moving beyond general generation - which relies on exhaustive prompt-engin
arXiv:2609.39266v1 Announce Type: new Abstract: Fine-grained vision-language alignment in chest radiography enables zero-shot classification, grounding, and segmentation without task-specific annotati
arXiv:2609.40287v1 Announce Type: new Abstract: Physics-constrained generative models aim to generate physical fields that match a target distribution and satisfy prescribed constraints. However, enfo
arXiv:2609.38427v1 Announce Type: cross Abstract: Major venues now publish detailed rules about how authors, reviewers, and area chairs may use AI, and those rules differ by role, by task, and by what
arXiv:2609.38458v1 Announce Type: new Abstract: Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Pri
arXiv:2603.24528v2 Announce Type: replace Abstract: Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that
arXiv:2609.40131v1 Announce Type: cross Abstract: Rank-constrained tensor neural networks reduce the parameterization of high-order inputs, but they do not explicitly constrain class geometry in the l
arXiv:2609.39789v1 Announce Type: cross Abstract: Real-world time series forecasting systems operate under non-stationary data streams, where forecasting performance may degrade over time. Although re
arXiv:2609.39223v1 Announce Type: new Abstract: Large language model (LLM) inference is increasingly moving toward lower precision to realize the throughput of hardware accelerators, but aggressive po
arXiv:2609.39164v1 Announce Type: new Abstract: Score-based variational inference (VI) provides an alternative to Kullback--Leibler (KL)-based VI by minimizing the Fisher divergence between the variat
arXiv:2609.39551v1 Announce Type: new Abstract: Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experim
arXiv:2609.38971v1 Announce Type: cross Abstract: Embodied vision-language models (VLMs) are increasingly deployed as high-level planners for robots because they generalize across diverse environments
arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing
arXiv:2609.39934v1 Announce Type: cross Abstract: Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable probab
Remote work is so cooked If your job can be done on the other side of a screen the AI can do it better Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to i