Knowledge catalogue
arXiv:2606.20310v2 Announce Type: replace Abstract: Video reward models are central to aligning video diffusion models with human preferences, yet existing ones are external vision-language models tha
arXiv:2610.17593v1 Announce Type: cross Abstract: Language provides a natural interface for humans to specify and reason about goals, but training language-conditioned robotic policies and reasoning t
arXiv:2610.18189v1 Announce Type: new Abstract: Modern text-to-video (T2V) models generate visually compelling videos, yet meaning-preserving changes in prompt wording can substantially alter semantic
arXiv:2610.18858v1 Announce Type: new Abstract: Multimodal large language models have advanced rapidly, but most remain optimized for single-image inputs. Multi-image reasoning is costly because each
arXiv:2610.17986v1 Announce Type: new Abstract: A common practice in instance retrieval is to grow the gallery size to improve a benchmark's discrimination capability. One prominent example is ILIAS,
arXiv:2610.18869v1 Announce Type: cross Abstract: How should demonstration quality be used during vision-language-action (VLA) pretraining to improve performance after target-task fine-tuning? We comp
arXiv:2610.14802v1 Announce Type: new Abstract: End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a v
Managing AI model access across dozens or hundreds of AWS accounts creates friction when each account must accept AWS Marketplace Private Pricing Offers individually. This post shows two ways to activ
When we talk about agents, that doesn't necessarily mean we're talking about Python. In today's modern ecosystem, an agent might run as a high-concurrency Go microservice on Cloud Run, or live inside
Silicon chip startup xMEMS Labs Inc. today said it has started mass production of its XMC-2400 and XMC-4800 chips for cooling artificial intelligence hardware. No one has commercialized solid-state ac
arXiv:2610.13929v1 Announce Type: new Abstract: Robot policies often convert sensing and control into fixed-rate observation-action sequences, leaving physical time implicit in sequence position. This
Learn how to deploy decision models with llama.cpp on Amazon SageMaker AI. This technical how-to serves OpenAI-compatible chat completions with the AWS Deep Learning Container for llama.cpp, then exte
arXiv:2610.12796v1 Announce Type: cross Abstract: Audio-visual speech enhancement (AVSE) improves speech intelligibility in noisy environments but often relies on computationally expensive models unsu
arXiv:2610.13117v1 Announce Type: new Abstract: Vision-language-action (VLA) models and world action models (WAMs) have advanced robotic policy learning by building on pretrained vision-language model
Agents are only as capable as the context they can reach. An agent with reliable access to the right information makes decisions grounded in fact; one without it guesses. And the work agents produce i
🚀 Introducing MiniCPM-V 4.7, our new open-source MLLM series! Advancing the Performance–Efficiency Pareto Frontier. It brings strong multimodal capabilities to iOS and Android devices with extreme eff
Paper: Looped Diffusion Transformer (arXiv 2609.40305, 30 Sep). Instead of making a text-to-image DiT bigger, it runs a shared group of transformer blocks several times inside each denoising step. The
arXiv:2610.13334v1 Announce Type: new Abstract: Motivated by the success of large language models (LLMs) with broad generalizability and robustness to noisy or unreliable pre-training data, we explore
arXiv:2610.13171v1 Announce Type: new Abstract: Power sampling improves large language model (LLM) reasoning at test time by sampling from a sharpened version of the base model's distribution. Its sam
arXiv:2610.13008v1 Announce Type: new Abstract: In repeated human-AI interaction, a single observation can be quoted, summarized, and returned to a model as multiple reports, making repetition look li
arXiv:2610.12769v1 Announce Type: cross Abstract: Unlearning in large reasoning models (LRMs) requires removing forget-set information from both the reasoning trace and the final answer. Existing appr
arXiv:2610.13453v1 Announce Type: new Abstract: Reinforcement Learning (RL) substantially improves planning performance in autonomous-driving Vision-Language-Action (VLA) models. However, existing RL
ReplaySSM stores an SSM state as a high‑precision checkpoint plus a buffer of recent inputs, cutting memory traffic by ~50 % and accelerating SSM decoding kernels on NVIDIA Blackwell Ultra B300 GPUs b
arXiv:2610.13317v1 Announce Type: new Abstract: Partial differential equation (PDE) surrogate modeling often relies on either dense observations or access to governing equations/physics constraints. I
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaffolds mitigate it wi
arXiv:2610.12602v1 Announce Type: cross Abstract: Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part
arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short a
arXiv:2610.13034v1 Announce Type: new Abstract: Trajectory extrapolation from a partial target trajectory is underdetermined, but completed related trajectories provide information about the unresolve
arXiv:2610.13348v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to answer questions over long interaction histories, where relevant evidence may be scattered across distant sessi
This is how we built the filesystem behind Perplexity Projects as a Git forge for agents. Each agent works in its own sandbox and commits to a shared repository where people and other agents can build
arXiv:2506.02955v3 Announce Type: replace-cross Abstract: Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation
arXiv:2508.02161v2 Announce Type: replace Abstract: Trajectory prediction is essential for formulating proactive strategies that anticipate user mobility and support advance preparation. Therefore, ho
arXiv:2610.13211v1 Announce Type: cross Abstract: Generative machine learning has shown remarkable results across a wide range of interdisciplinary tasks, motivating significant efforts toward Quantum
arXiv:2610.13465v1 Announce Type: cross Abstract: Multimodal LLMs can fail to read text embedded in an image's coarse structure (text a human recovers by squinting) and report that no text is present.
https://preview.redd.it/9k5fw4j47puh1.png?width=545&format=png&auto=webp&s=ff0a6ff6fb69ae9a9bcd579bd612c553fc3e2a00 https://preview.redd.it/xcwzlmo77puh1.png?width=664&format=png&auto=webp&s=c8a637e2e
The artificial intelligence infrastructure race is no longer just about building faster chips. AI infrastructure bottlenecks are shifting attention to a bigger challenge: keeping those chips supplied
arXiv:2610.11149v1 Announce Type: new Abstract: Video anomaly detection (VAD) is a fundamental and safety-critical task in computer vision. Recent generative approaches detect anomalies from a distrib
Ai2 joined COLM 2026 to share advances in open language models, training infrastructure, and AI for science, including Olmo Hybrid, Asta, and Bolmo, while connecting with the broader research communit
arXiv:2610.11527v1 Announce Type: new Abstract: Atomistic simulation is a fundamental tool for studying long-term materials evolution, from diffusion and defect dynamics to interfacial reactions and f
arXiv:2610.12307v1 Announce Type: new Abstract: Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-sized image patches. This static pa
Bullish on this trend of making post-training more accessible. A new post-training era is upon us. If you work on agentic RL, long-context tasks (a big focus today) are expensive, inefficient, and don
arXiv:2502.17920v2 Announce Type: replace Abstract: Pre-trained visual models have become fundamental in computer vision, but they face challenges in continual learning scenarios where data and tasks
arXiv:2610.11971v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies assume the embodiment on which they were trained and can fail when a joint fault changes how commanded actions a
arXiv:2610.11784v1 Announce Type: new Abstract: Tabular in-context learning (ICL) has emerged as a training-free and accurate paradigm for tabular prediction, but current approaches to compressing its
arXiv:2610.12437v1 Announce Type: cross Abstract: Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view
arXiv:2610.11826v1 Announce Type: cross Abstract: Object hallucination remains a major obstacle for large vision-language models (LVLMs) to generate reliable content. An intuitive mitigation strategy
arXiv:2610.12213v1 Announce Type: cross Abstract: Bayesian Optimization (BO) is a popular method for efficiently optimizing expensive black-box objectives. However, BO utilizing standard Gaussian Proc
arXiv:2610.11546v1 Announce Type: cross Abstract: Solving high-dimensional structural model updating problems requires an algorithm capable of navigating complex, non-convex landscapes with correlated
arXiv:2610.11634v1 Announce Type: cross Abstract: Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instr
arXiv:2610.12293v1 Announce Type: cross Abstract: Machine learning (ML) in high-energy nuclear physics (HENP) is entering a new stage in which physical knowledge is incorporated more directly into dat
arXiv:2610.11228v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong potential for sequential recommendation through their ability to reason over complex m
arXiv:2610.10655v1 Announce Type: cross Abstract: Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning
arXiv:2609.33987v2 Announce Type: replace Abstract: Long-horizon coding agents need timely corrections, yet feedback can be ineffective or even harmful when it misjudges ongoing work or fails to addre
arXiv:2610.11342v1 Announce Type: new Abstract: Synergistically capturing intricate local structures and global contextual dependencies has become a critical challenge in point cloud representation le
arXiv:2510.25257v2 Announce Type: replace Abstract: Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the p
arXiv:2610.10563v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often answer visual reasoning questions by relying on linguistic priors rather than task-relevant visual evid
arXiv:2610.12402v1 Announce Type: cross Abstract: Existing spatial reasoning benchmarks mainly test spatial perception: reading off relations already visible in the input. Yet real-world spatial intel
arXiv:2610.11579v1 Announce Type: new Abstract: To adapt billion-parameter Vision Transformers for long-video understanding, recent methods freeze the backbone and train lightweight convolutional modu
arXiv:2610.11617v1 Announce Type: cross Abstract: Knowledge distillation enables efficient spatiotemporal prediction by transferring knowledge from an accurate teacher to a compact student. However, m
arXiv:2610.11504v1 Announce Type: new Abstract: Modern autonomous driving systems rely on bird's-eye-view (BEV) perception models that fuse camera and LiDAR inputs to detect objects in 3D space. These