Knowledge catalogue
arXiv:2609.39245v1 Announce Type: new Abstract: In interactive scenarios, an autonomous driving system is required to generate ego actions under the influence of other agents' behaviors. Existing Worl
arXiv:2609.39685v1 Announce Type: cross Abstract: Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstration
arXiv:2601.08355v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for saf
arXiv:2609.38987v1 Announce Type: new Abstract: Preference distillation typically treats a teacher response as preferred and the student's own response as rejected. This assumes that self-generated fa
arXiv:2609.39091v1 Announce Type: cross Abstract: Inference-time alignment of flow and diffusion-based models is critical for achieving flexible generative modeling. Theoretically, Doob's h-transform
arXiv:2609.38205v1 Announce Type: new Abstract: System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the trans
arXiv:2609.38274v1 Announce Type: new Abstract: The performance ceiling of an LLM team is constrained not only by individual model capabilities, but also by inter-member error resonance and predictive
Viola Zhou / Rest of World: Alibaba's ModelScope and OSChina's MoArk are vying to become Chinese alternatives to Hugging Face; ModelScope hosts 170K+ open models, while MoArk hosts ~20K — AI model pla
arXiv:2609.36771v1 Announce Type: cross Abstract: Root cause analysis (RCA) is a critical problem in many real-world scenarios. RCA enables the identification of faulty or failing mechanisms in a syst
arXiv:2609.35841v1 Announce Type: cross Abstract: Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However, traditional rule-based tools often generate l
arXiv:2609.36305v1 Announce Type: new Abstract: World models jointly learn latent representations and dynamics that predict how high-dimensional observations evolve under actions. In this work, we pro
arXiv:2609.36630v1 Announce Type: new Abstract: Modern agents increasingly rely on memories, tools, and execution logic, so their competence extends beyond model parameters. This shift exposes a limit
arXiv:2609.36106v1 Announce Type: cross Abstract: We study the fundamental limits of transferability in algebraic signal processing through homomorphisms between algebraic signal models. Homomorphisms
arXiv:2609.37700v1 Announce Type: new Abstract: Language models expose internal signals that predict whether an answer is correct, readable from a single forward pass of a frozen model without additio
arXiv:2609.38078v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited
arXiv:2609.36903v1 Announce Type: cross Abstract: End-to-end full-duplex speech models have brought open-source machine conversation closer to human-like interaction, yet existing systems remain limit
arXiv:2609.36224v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) combine image generation and visual understanding in a shared backbone. Since generation and understanding are invers
arXiv:2602.13540v2 Announce Type: replace-cross Abstract: Accurate confidence estimation is critical for reliable use of large language models (LLMs). Prior work on LLM calibration largely focuses on
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The mo
arXiv:2609.36638v1 Announce Type: cross Abstract: Text-to-image users often provide concise and underspecified prompts, whereas generative models benefit from detailed textual conditions for reliable
arXiv:2609.36684v1 Announce Type: new Abstract: Embodied agents now take on ever longer tasks. For long tasks, knowing only whether a task finally succeeds or fails says little; the steps along the wa
arXiv:2609.36680v1 Announce Type: new Abstract: Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In vi
arXiv:2609.36982v1 Announce Type: cross Abstract: Knowledge concept tagging aims to assign specific concept or topic labels to educational content, which is essential for both educators and learners i
arXiv:2609.35860v1 Announce Type: cross Abstract: Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors ar
arXiv:2609.37132v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) improves large language models by letting a self-teacher with privileged information provide dense token-level superv
arXiv:2609.34035v1 Announce Type: new Abstract: Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigati
arXiv:2609.31989v1 Announce Type: cross Abstract: We study communication between two frozen large language models from different providers, with different tokenizers, accessed through their API endpoi
arXiv:2609.32932v1 Announce Type: new Abstract: Finite computational resources force a tradeoff between automatic System 1 processes and costly System 2 thinking. Large language models (LLMs) can spen
arXiv:2609.33490v1 Announce Type: cross Abstract: Conditional independence (CI) is a fundamental concept in statistics and machine learning. Recent advances in conditional generative modeling provide
arXiv:2609.31997v1 Announce Type: new Abstract: Decoding imagined speech is an important goal for brain-computer interfaces but remains challenging due to weak neural responses, low signal-to-noise ra
arXiv:2510.02284v4 Announce Type: replace Abstract: Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond thei
arXiv:2609.33521v1 Announce Type: new Abstract: Trust evaluation plays a critical role in cybersecurity by supporting risk mitigation and decision-making. A variety of trust evaluation methods have be
arXiv:2609.35579v1 Announce Type: new Abstract: Residual stream pruning methods reduce inference cost by shrinking the model's hidden dimension, but existing approaches typically choose these dimensio
arXiv:2609.35768v1 Announce Type: new Abstract: Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) r
arXiv:2609.34466v1 Announce Type: new Abstract: Physiological foundation models encode how a signal was recorded alongside the physiology it reflects. When recording conditions are associated with dia
arXiv:2609.34031v1 Announce Type: new Abstract: We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational exte
arXiv:2609.34061v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models integrate pretrained Vision-Language Models (VLMs) with action heads for robot control. Common action heads have d
arXiv:2609.33218v1 Announce Type: new Abstract: Visual world models enable robotic planning by predicting future observations, but dense latent-state propagation and sample-intensive trajectory optimi
arXiv:2609.34235v1 Announce Type: new Abstract: Medical image segmentation remains challenging in practical deployment, as models often struggle to generalize beyond the distributions covered by their
arXiv:2609.32676v1 Announce Type: new Abstract: Time Series Foundation Models (TSFMs) have achieved remarkable zero-shot performance through extensive pre-training on massive time series datasets. Nev
arXiv:2609.35504v1 Announce Type: new Abstract: Machine intelligence is often evaluated through abstract reasoning problems, yet many real-world problems are visual, such as arranging objects, repairi
arXiv:2607.18580v2 Announce Type: replace Abstract: Natural-language robot instructions often specify more than a coarse task goal: they may impose spatial, temporal, and logical requirements that mus
arXiv:2609.35002v1 Announce Type: new Abstract: Visual token compression reduces the inference cost of Large Vision-Language Models (LVLMs). However, aggregate robustness measures do not reveal whethe
arXiv:2609.35224v1 Announce Type: new Abstract: Masked-diffusion language models fill in masked positions in parallel and in no fixed order. Most practical text watermarks assume left-to-right generat
When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content survive
Took a while, but here it is, a mega write-up on language models for text classification and, of course, Jev. It's basically a visual guide to RNNs, CNNs, transformers, and calibration, with hands-on
arXiv:2609.35609v1 Announce Type: new Abstract: Constrained decoding for Masked Diffusion Language Models (MDLMs) aims to ensure that generated outputs satisfy a specified structure or syntax constrai
arXiv:2609.31456v1 Announce Type: new Abstract: Vision-language models (VLMs) often struggle with compositional reasoning tasks, but the reasons for this underperformance remain unclear. A common hypo
arXiv:2511.20561v3 Announce Type: replace-cross Abstract: Recent years have witnessed significant progress in Unified Multimodal Models, yet a fundamental question remains: Does understanding truly in
arXiv:2609.30763v1 Announce Type: new Abstract: Biomedical language models (LMs) encode textual semantics but do not explicitly preserve medical code hierarchies. We present Hyperbolic Clinical Ontolo
arXiv:2609.30995v1 Announce Type: new Abstract: Machine learning (ML) emulators provide a fast and cost-effective method to simulate climate change scenarios after being trained on Earth System Models
Tom Wilson / Financial Times: Google Threat Intelligence Group finds dark web marketplaces selling access to AI models, including from Anthropic, Google, and OpenAI, at up to 97% discounts — Security
arXiv:2609.28940v1 Announce Type: cross Abstract: Autonomous penetration-testing harnesses use large language models (LLMs) for reconnaissance, exploitation, and reporting, but often rely on those sam
arXiv:2609.30243v1 Announce Type: new Abstract: Dedicated decision models such as Jev map unstructured language to probability distributions over finite choices, allowing their outputs to directly rou
arXiv:2609.28682v1 Announce Type: new Abstract: Post-training hybrid reasoning models in NoThink mode has attracted growing interest as a way to improve performance while keeping inference fast. Howev
arXiv:2609.29048v1 Announce Type: new Abstract: Unified vision-language models (VLMs) that tokenize images through a vector-quantized (VQ) codebook routinely hallucinate objects on grounded yes/no ben
btw i had no idea what i was doing when i started this but learned so much about models in the process and feel like i have a much better sense of what’s happening under the hood managing someone (an
I was having trouble searching and analyzing the different models that Ollama has available ( https://ollama.com/library ). I wanted to filter for specific model sizes and tooling capabilities, so I b
arXiv:2609.28262v1 Announce Type: new Abstract: Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inf
arXiv:2609.28272v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have attracted significant attention for their strong reasoning ability. However, under a bidirectional attention mecha