Knowledge catalogue
arXiv:2610.11328v1 Announce Type: new Abstract: Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intell
arXiv:2510.04532v2 Announce Type: replace Abstract: Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting
arXiv:2610.12030v1 Announce Type: new Abstract: Large Language Models (LLMs) have renewed interest in autoformalization. Yet, when First-Order Logic (FOL) is considered as the target formalism, the fi
arXiv:2610.11498v1 Announce Type: new Abstract: Video diffusion and flow models require many sequential evaluations, making generation computationally expensive. Few-step distillation reduces this cos
arXiv:2610.11329v1 Announce Type: new Abstract: Pathology vision-language models (VLMs) have shown strong visual perception ability, but their robustness in the language domain remains poorly characte
arXiv:2610.12176v1 Announce Type: new Abstract: Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed
arXiv:2610.12233v1 Announce Type: cross Abstract: Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to pra
arXiv:2610.11645v1 Announce Type: new Abstract: As orbital populations grow, conjunction screening must search more object pairs for potential collision risks. Existing pipelines use early-stage filte
arXiv:2603.08260v2 Announce Type: replace Abstract: Existing data generation methods for robot learning suffer from limited exploration, embodiment gaps, low signal-to-noise ratios, and domain shifts,
arXiv:2610.10549v1 Announce Type: new Abstract: Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely constrained due to business and leg
arXiv:2610.11765v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly ship with explicit 'thinking modes', yet their counterpart, 'no-thinking', has received far less attention. We
Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel
arXiv:2610.11105v1 Announce Type: new Abstract: Generating high-quality and controllable camera motion is essential for AI-assisted cinematography, video synthesis, and 3D scene understanding. We intr
arXiv:2610.11948v1 Announce Type: new Abstract: Reliable multimodal interaction depends on selective use of conversational history: an earlier question may remain relevant while its previous answer is
arXiv:2610.11184v1 Announce Type: new Abstract: Advances in image generation have made visual authenticity increasingly difficult to assess. Although image forensics now examines both generation artif
arXiv:2610.09677v1 Announce Type: new Abstract: Self-supervised anomaly detection is a promising paradigm for medical ultrasound, as normal images are often easier to obtain than exhaustive annotation
arXiv:2610.10047v1 Announce Type: new Abstract: Product-centric advertisement video generation aims to create promotional videos that preserve fine-grained product identity while presenting selling po
arXiv:2610.09240v1 Announce Type: cross Abstract: Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser action
arXiv:2610.09764v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate drone programs from natural-language mission descriptions, but syntactically valid programs may still violate
arXiv:2505.21468v2 Announce Type: replace Abstract: We present Causal Posterior Estimation (CPE), a novel method for Bayesian inference in simulator models, where evaluating the likelihood function is
arXiv:2610.09229v1 Announce Type: new Abstract: LLM-as-judge is now a standard tool for scalable evaluation, but judge performance is still often summarized by a single accuracy number. This aggregate
arXiv:2610.09107v1 Announce Type: cross Abstract: Natural-language feedback in interactive learning often explains why an action failed by pointing to violated requirements. Misinterpreting this feedb
Enterprises racing to put agents into production are learning that the AI improvement loop never really ends. Agents must be run, observed, evaluated and improved continuously. CoreWeave Inc. has been
arXiv:2610.10436v1 Announce Type: new Abstract: Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity pa
arXiv:2610.09321v1 Announce Type: new Abstract: Speech Language Model (SLM) performance often degrades on dialects due to data scarcity. Conventional text-to-speech (TTS) augmentation struggles to cov
arXiv:2506.11481v2 Announce Type: replace Abstract: Scene Change Detection (SCD) evaluates changes using predefined query-reference (i.e., present-past) image pairs. However, this formulation overlook
arXiv:2609.35308v2 Announce Type: replace Abstract: Large language models treat conversation history as unverified context, so false premises injected into prior turns can be adopted as fact, a failur
arXiv:2510.19773v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) have emerged as the standard tool for evaluating the privacy risks of AI models. However, state-of-the-art attac
arXiv:2610.10423v1 Announce Type: new Abstract: Adversarial example detectors are often tied to the classifier backbone they were trained on, limiting reuse when the protected model is replaced or upg
arXiv:2610.09824v1 Announce Type: new Abstract: Multi-agent systems (MAS) leverage interactions between agents to perform complex tasks. Despite their success, we show that these interactions can also
arXiv:2610.10203v1 Announce Type: new Abstract: Model organisms of alignment-relevant behaviors (e.g., backdoors, sycophancy, spurious correlations) have emerged as a key tool for evaluating whitebox
arXiv:2610.09534v1 Announce Type: new Abstract: Rotational symmetry is an important prior in 6D pose estimation, improving pose accuracy and supporting symmetry-aware evaluation. However, current symm
arXiv:2610.08858v1 Announce Type: new Abstract: Low-rank compression reduces the cost of pretrained language models by replacing linear transformations with low-rank factorizations. However, conventio
arXiv:2610.09795v1 Announce Type: new Abstract: The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap i
arXiv:2610.09209v1 Announce Type: new Abstract: Substance Use Disorder (SUD) counseling requires patient responses that reflect underlying cognitive states such as beliefs, coping strategies, and read
arXiv:2610.08994v1 Announce Type: cross Abstract: Speech large language models (speech LLMs) perform well on automatic speech recognition (ASR) when sufficient paired speech-text data is available, bu
arXiv:2610.09382v1 Announce Type: cross Abstract: Scribble-based interaction provides a lightweight and intuitive way for users to specify image editing intents in interactive editing tools. However,
arXiv:2610.10304v1 Announce Type: cross Abstract: We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference. We int
arXiv:2610.09384v1 Announce Type: new Abstract: Language models are routinely fine-tuned under a fixed context, such as a generic system prompt, persona or domain-specific instruction, yet the learned
arXiv:2604.01569v2 Announce Type: replace Abstract: Video multimodal large language models achieve strong results on existing benchmarks, but answer accuracy alone does not establish whether they can
arXiv:2610.08828v1 Announce Type: new Abstract: Small-data adaptation can improve speech detection while degrading speaker attribution. We study this discrepancy in a released streaming diarizer adapt
arXiv:2610.07071v1 Announce Type: new Abstract: The quality of computed tomography (CT) images is significantly affected by the selection of reconstruction kernels: sharp kernels improve spatial resol
arXiv:2610.07356v1 Announce Type: cross Abstract: Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that t
arXiv:2610.07191v1 Announce Type: cross Abstract: Modern edge Systems-on-Chip (SoCs) integrate heterogeneous processing units (PUs) such as CPUs, GPUs, and NPUs, each with distinct performance and ene
arXiv:2510.22954v2 Announce Type: replace Abstract: Language models (LMs) often struggle to generate diverse, human-like creative content, raising concerns about the long-term homogenization of human
arXiv:2610.08446v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physic
arXiv:2610.07323v1 Announce Type: cross Abstract: Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive m
arXiv:2601.17645v2 Announce Type: replace-cross Abstract: Internet audio-visual clips convey meaning through time-varying sound and motion, which extend beyond what text alone can represent. To examin
arXiv:2610.08450v1 Announce Type: new Abstract: Autonomous vehicles (AVs) have significantly advanced in real-world deployment in recent years, yet safety continues to be a critical barrier to widespr
arXiv:2610.08101v1 Announce Type: new Abstract: Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and fail
arXiv:2610.07105v1 Announce Type: cross Abstract: Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its lates
arXiv:2610.07019v1 Announce Type: new Abstract: Fiorillo v0.5 is an open model that answers typed questions with a probability for each answer. Its main specialist reads a randomized trial's article,
arXiv:2610.07219v1 Announce Type: new Abstract: Mixture-of-experts models make nearly trillion-parameter capacity accessible with sparse per-token computation, provided that the serving system can dis
arXiv:2610.07939v1 Announce Type: new Abstract: Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both huma
arXiv:2610.07557v1 Announce Type: cross Abstract: Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and re
arXiv:2610.07489v1 Announce Type: cross Abstract: Increasing connectivity to the outside world and the lack of inbuilt security mechanisms have made legacy intra-vehicular networks vulnerable to cyber
arXiv:2610.08780v1 Announce Type: cross Abstract: World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and pl
arXiv:2610.08722v1 Announce Type: new Abstract: Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's r
arXiv:2610.06970v1 Announce Type: new Abstract: Egocentric bimanual hand pose estimation is important for virtual interaction, wearable control, and rehabilitation, but visual observations are often d
arXiv:2610.08367v1 Announce Type: new Abstract: Several discrete design tasks, such as molecular discovery, require diverse collections of useful candidates at low computational cost. High validity al