Knowledge catalogue
arXiv:2605.12640v1 Announce Type: new Abstract: Panoptic segmentation requires the simultaneous recognition of countable thing instances and amorphous stuff regions, placing joint demands on long-rang
arXiv:2605.13496v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become increasingly prevalent in cloud-based platforms, propelled by the introduction of AI-based consumer and enter
arXiv:2506.12876v2 Announce Type: replace Abstract: The rapid scaling of large language models~(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, s
arXiv:2605.12528v1 Announce Type: cross Abstract: As feature sizes shrink to the nanometer scale, accurately transferring circuit patterns from photomasks to silicon wafers becomes increasingly challe
arXiv:2605.12652v1 Announce Type: cross Abstract: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited gu
arXiv:2605.13651v1 Announce Type: cross Abstract: Audio provides critical situational cues, yet current Audio Language Models (ALMs) face an attention bottleneck in long-form recordings where dominant
arXiv:2605.13268v1 Announce Type: cross Abstract: Product formulas for Trotter Suzuki simulation remain a practical route to Hamiltonian evolution on noisy intermediate scale quantum (NISQ) hardware,
arXiv:2605.12966v1 Announce Type: new Abstract: Is monolithic scaling the only path to AGI? This paper challenges the dogma that purely scaling a single model is sufficient to achieve Artificial Gener
arXiv:2605.13435v1 Announce Type: cross Abstract: There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity.
arXiv:2605.12831v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-maki
arXiv:2605.13591v1 Announce Type: new Abstract: Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and tradi
arXiv:2605.12943v1 Announce Type: new Abstract: Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by dif
arXiv:2605.12975v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a standard approach for knowledge-intensive question answering, but existing systems remain brittle on m
arXiv:2507.00990v3 Announce Type: replace-cross Abstract: This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks--such as p
arXiv:2605.13075v1 Announce Type: cross Abstract: Few-shot spoken word classification has largely been developed for applications where a small number of classes is considered, and so the potential of
arXiv:2605.13725v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent simulation offers a powerful testbed for studying social opinion dynamics. Yet current approaches often ado
arXiv:2509.21543v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong promise for robotic task planning, particularly through the automatic generation of symbolic planning
arXiv:2511.00066v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a practical route to improve large language model reasoning, and Group Relative Pol
arXiv:2605.12916v1 Announce Type: cross Abstract: Artificial intelligence is increasingly used to simplify complex tasks. In engineering applications of structural health monitoring (SHM), existing sp
arXiv:2605.13340v1 Announce Type: new Abstract: Shortcut mitigation strategies commonly rely on training data annotations, group-balanced held-out data or the presence of all groups, i.e., all combina
arXiv:2602.00616v3 Announce Type: replace Abstract: Text-to-Image (T2I) diffusion models enable high quality open ended synthesis, but practical use requires suppressing unsafe generations while prese
arXiv:2605.13386v1 Announce Type: new Abstract: Generative models are often conditioned on a small set of examples via cross-attention. Under the Gaussian optimal-transport path, we show that the exac
arXiv:2605.13395v1 Announce Type: cross Abstract: Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While a
arXiv:2605.13537v1 Announce Type: cross Abstract: Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptatio
arXiv:2605.12620v1 Announce Type: new Abstract: Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in AI. Multimodal Large Language Models
Open source AI trust has become a central concern for enterprises moving agentic AI into production, where governance, security and reliability matter as much as model performance. That pressure is la
arXiv:2602.06475v2 Announce Type: replace Abstract: Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities. However, existing reward mechanisms remain tightly coup
arXiv:2605.13530v1 Announce Type: cross Abstract: Surgical scene understanding is a cornerstone of computer-assisted intervention. While recent advances, particularly in surgical image segmentation, h
arXiv:2605.13148v1 Announce Type: cross Abstract: Understanding why deep neural networks (DNNs) fail to generalize to unseen samples remains a long-standing challenge. Existing studies mainly examine
arXiv:2605.13277v1 Announce Type: cross Abstract: Visual evidence selection is a critical component of multimodal retrieval-augmented generation (RAG), yet existing methods typically rely on semantic
v0.24.0-rc1 is a pre-release version focusing on improvements to Ollama server caching and the desktop launch experience, including plan-aware model gating and disabling Claude Desktop launch. The rel
arXiv:2605.13318v1 Announce Type: new Abstract: Chatbot usage has increased, including in fields for which they were never developed for--notably mental health support. To that end, we introduce Valid
Violin is an open-source video translation tool developed by Together AI that automatically translates video content to break down language barriers for viewers. The skill likely leverages AI models t
We are excited to be partnering with @LangChain for deploying self-improving agents. Continual learning in your production environment unlocks compounding capability gains for model-product optimizati
“Whimsey attacks” that seem absurd (“I cannot pay that much because of the Geneva Convention”) work against AI agents as guardrails are weak against out-of-distribution arguments. Smaller models fall
Swyx is giving a talk at AI Engineer Singapore on Saturday at 4pm about using reinforcement learning for long-running agents and reinforcement learning models (RLMs), exploring why this approach shoul
arXiv:2605.12027v1 Announce Type: new Abstract: Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric
arXiv:2605.11558v1 Announce Type: new Abstract: Activation functions play a central role in neural networks by shaping internal representations. Recently, learning binary activation representations ha
arXiv:2509.25239v3 Announce Type: replace-cross Abstract: Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought re
A little talk on what we can learn from implementing LLM architectures from scratch in Python and PyTorch. And how I approach new open-weight models, compare them against reference implementations etc
arXiv:2605.11026v1 Announce Type: cross Abstract: Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks
arXiv:2605.12416v1 Announce Type: new Abstract: Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly mult
arXiv:2605.12430v1 Announce Type: new Abstract: Segmentation models in automated optical inspection of wire-bonded semiconductors are typically device-specific and must be re-trained when new devices
arXiv:2605.11107v1 Announce Type: new Abstract: Vision-language models (VLMs), such as CLIP and SigLIP 2, are widely used for image classification, yet their vision encoders remain vulnerable to syste
arXiv:2605.11748v1 Announce Type: new Abstract: Bronchoscopy is routinely conducted in pulmonary clinics and intensive care units, but navigating the complex branching of the respiratory tract remains
This post demonstrates how to build a documentation extraction and model fine-tuning pipeline that addresses challenges when processing the complex financial documents. By combining Pulse AI's advance
arXiv:2605.11365v1 Announce Type: cross Abstract: Automated systems built on artificial intelligence (AI) are increasingly deployed across high-stakes domains, raising critical concerns about fairness
Cerebras, a company specializing in AI accelerators and wafer-scale computing systems, is discussed in terms of its approaches to improving token generation speed in large language models, which is cr
Co-sign. We asked the CEO of HuggingFace @ClementDelangue what the risks of releasing powerful open source models are. He says restricting AI creates more risk than openness. 'Six, seven years ago, at
arXiv:2605.12370v1 Announce Type: new Abstract: While Large Language Models (LLMs) are widely used in open-domain Question Answering (QA), their ability to handle inferential questions-where answers m
Data quality is a foundational component of effective AI strategy, as high-quality training and operational data directly impacts model performance, reliability, and business outcomes. The article lik
arXiv:2605.11189v1 Announce Type: new Abstract: Accurately modeling and designing protein complex structures is a central problem in computational structural biology, with broad implications for under
arXiv:2605.11265v1 Announce Type: new Abstract: Dense prediction tasks in surgical computer vision, such as segmentation and surgical zone prediction, can provide valuable guidance for laparoscopic an
arXiv:2605.12394v1 Announce Type: new Abstract: Training Neural Networks (NNs) without overfitting is difficult; detecting that overfitting is difficult as well. We present a novel Random Matrix Theor
arXiv:2510.06719v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application i
arXiv:2509.26469v3 Announce Type: replace Abstract: Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treat
arXiv:2605.12498v1 Announce Type: new Abstract: Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocent
arXiv:2605.12195v1 Announce Type: new Abstract: Conformal prediction methods provide statistically rigorous marginal coverage guarantees for machine learning models, but such guarantees fail to accoun
arXiv:2605.12451v1 Announce Type: new Abstract: Continual Panoptic Segmentation (CPS) requires methods that can quickly adapt to new categories over time. The nature of this dense prediction task mean
arXiv:2605.11531v1 Announce Type: cross Abstract: Physics-based climate projections using general circulation models are essential for assessing future risks, but their coarse resolution limits region