Search: “models”

arXiv:2610.21007v1 Announce Type: new Abstract: Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds. Different allocation

arXiv:2610.22193v1 Announce Type: new Abstract: In robotic manipulation, the same observation often admits multiple feasible actions. Generative policies such as diffusion and flow matching naturally

arXiv:2610.21979v1 Announce Type: cross Abstract: End-to-end full-page document parsing must preserve the content and structure of heterogeneous elements, yet otherwise accurate outputs can contain lo

arXiv:2507.18903v2 Announce Type: replace-cross Abstract: Causal identification asks whether a causal target can be recovered from the observational distribution in an idealized infinite-data setting.

arXiv:2610.20739v1 Announce Type: new Abstract: Quantile forecasts summarize uncertainty at each future time step, while diffusion forecasters represent it through sampled future trajectories. We stud

https://preview.redd.it/tu63jjp1juvh1.png?width=1200&format=png&auto=webp&s=ee61a9b9212a6d4e3e3a113d8c0f60e3fd25db53 I RLed qwen27b in style of RL XAR by meta, and now its doesnt feel like a sloppy mo

I got Qwen3.8-Flash-Next-GSQ-RCO-Abliterated running at IQ3_S with just 12GB VRAM + 32GB RAM + NVME, achieving 40-50 tok/sec decode & 1300-1500 tok/sec prefill @ 131k context (44k thinking budget), on

arXiv:2610.20935v1 Announce Type: new Abstract: Engineering agents must produce artifacts that satisfy exact, coupled constraints. Existing solutions often require agents to make semantic decisions an

arXiv:2510.08667v3 Announce Type: replace-cross Abstract: Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA t

Software development startup RapidCanvas Inc. today announced that it has raised 29 million in funding. Vertex Ventures SEA & India led the Series B round with contributions from Hitachi Ventures, Acc

arXiv:2602.05785v2 Announce Type: replace-cross Abstract: Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining.

arXiv:2610.21682v1 Announce Type: cross Abstract: Reinforcement learning (RL) can become off-policy due to training-inference mismatch, mini-batch updates, and asynchronous training.The resulting mism

arXiv:2610.20959v1 Announce Type: cross Abstract: Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but thei

arXiv:2602.09432v2 Announce Type: replace Abstract: Current one-pass 3D scene synthesis methods often suffer from spatial hallucinations, such as collisions, due to a lack of deliberative reasoning. T

arXiv:2406.18397v4 Announce Type: replace-cross Abstract: In this article, we introduce the novel concept of the second maximum of a Gaussian random field defined on a Riemannian manifold: Once the fi

arXiv:2610.21188v1 Announce Type: new Abstract: Faulty sensor readings can distort estimates of fuel use and carbon dioxide emissions from diesel engines. We evaluate two procedures that use relations

arXiv:2610.21087v1 Announce Type: cross Abstract: We identify a theoretical incompatibility between 3D point cloud masked autoencoding and SE(3)-equivariant networks. We prove that standard masking tr

arXiv:2603.14645v2 Announce Type: replace Abstract: In this paper, we study the diffusability (learnability) of variational autoencoders (VAEs) in latent diffusion. We first derive distribution-free b

arXiv:2610.20960v1 Announce Type: new Abstract: Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and inter

arXiv:2610.22352v1 Announce Type: new Abstract: Single image 3D generation aims to dress a given 3D mesh with relightable materials while faithfully preserving the visual details of a reference image.

arXiv:2610.21895v1 Announce Type: new Abstract: Surgical teams could benefit from assistants that watch the video for requested events, such as 'tell me when the clip applier appears during Calot tria

arXiv:2610.20901v1 Announce Type: cross Abstract: Task-Oriented Grasping (TOG) has emerged as an important skill for purposeful robotic manipulation. Given the task of using a knife to 'slice bread,'

arXiv:2610.22157v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) reduce or eliminate the need for large labelled datasets by enforcing governing equations during training. Phys

arXiv:2610.21908v1 Announce Type: new Abstract: Many modern learning systems are used not to select a single best action, but to sample diverse high-quality outputs. Examples include entropy-regulariz

arXiv:2602.23959v2 Announce Type: replace Abstract: Recent MLLMs increasingly rely on visual chain-of-thought to perform region-grounded reasoning over images. However, existing approaches ground regi

arXiv:2610.21823v1 Announce Type: new Abstract: Retrieval tasks are a form of search task where a robot must explore, find an object, and return with it as quickly as possible. Recent work in ergodic

arXiv:2610.21515v1 Announce Type: new Abstract: Language-conditioned humanoid motion generation enables users to create and refine robot movements through natural language. The central challenge is to

arXiv:2610.21222v1 Announce Type: new Abstract: Artificial microbots capable of precise and autonomous navigation could provide versatile platforms for microscale transport, manipulation, and task exe

arXiv:2610.21601v1 Announce Type: cross Abstract: Policy-shift distillation reuses the difference between a teacher's log probabilities before and after reinforcement learning (RL) as supervision on s

arXiv:2610.20120v1 Announce Type: new Abstract: We present several advances on neural operators by viewing the action of operator layers as the minimizers of Bregman regularized optimization problems

arXiv:2610.20075v1 Announce Type: new Abstract: Federated learning over decentralized networks inherently trades off the suppression of local finite-sample noise through collaboration against the bias

arXiv:2510.12306v4 Announce Type: replace Abstract: As natural language corpora expand at an unprecedented rate, manual annotation remains a significant methodological bottleneck in corpus linguistic

arXiv:2610.20278v1 Announce Type: new Abstract: Facial image watermarking can support traceability and certification in biometric pipelines, but provenance or manipulation detection alone does not gua

arXiv:2610.20532v1 Announce Type: cross Abstract: A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no

arXiv:2610.20252v1 Announce Type: new Abstract: Deep reinforcement learning (DRL) policies for planetary landing and other aerospace guidance, navigation, and control tasks are commonly trained under

Agents need a better interface. In my own agent orchestrator, I often render more actionable, valuable outputs as small interfaces. @openuidev makes this easy for any AI app. It is an open-source, mod

arXiv:2610.14823v1 Announce Type: cross Abstract: Artificial intelligence is increasingly used to support product management tasks. At the same time, AI-native research and development (R&D) may incre

Amazon.com Inc. today debuted two new wearable, artificial intelligence-enabled devices aimed at making everyday life simpler by listening to conversations and helping users remember what matters. Bee

arXiv:2610.15795v1 Announce Type: cross Abstract: Automated moderation systems are deployed at scale, yet they remain opaque to the users and moderators affected by their decisions, and their coverage

arXiv:2610.15380v1 Announce Type: new Abstract: Bridging the structural gap between biological brains and artificial neural networks presents a pathway to altered computational dynamics. This paper in

arXiv:2610.14807v1 Announce Type: new Abstract: Evaluating autonomous agents requires examining whether they can translate goals into coherent action across extended interactions. In persistent enviro

arXiv:2610.19358v1 Announce Type: new Abstract: In this paper we study the behavior of transformer networks generating text over long periods of time. We show that even a three-token, single-layer att

arXiv:2610.20514v1 Announce Type: new Abstract: Evaluations of classifiers (AI or human or agents) often assume a batch setting in which every agent produces labels on every example in a test set, whi

First, kudos to Strata. It inspired this project, and while I was building it Strata got much faster and added NVFP4 support, which was my main reason for starting. By then I was too far in to stop, s

arXiv:2610.19761v1 Announce Type: new Abstract: Soft spectral clipping (SSC) reduces gradient singular values, but its effect depends on the gradient scale and clipping threshold. We introduce CAST (C

Agentic workflows are making speed a condition for whole classes of AI applications to exist, and the fastest tokens will determine which platforms win the next phase of AI. Cerebras Systems Inc., whi