Knowledge catalogue
arXiv:2608.21750v1 Announce Type: new Abstract: Parametric retrieval-augmented generation (PRAG) injects retrieved evidence into a large language model (LLM) through passage-specific LoRA adapters, re
arXiv:2608.22861v1 Announce Type: new Abstract: State Space Models (SSMs) have surfaced as a promising architecture in Video Frame Interpolation (VFI), as they can capture long-range dependencies with
arXiv:2608.22566v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems are designed to improve reasoning by decomposing tasks across multiple agents with specialized functions,
arXiv:2608.23045v1 Announce Type: new Abstract: Web search agents powered by Large Language Models (LLMs) show strong promise, but deep research tasks expose a recurring failure mode: once an agent ha
arXiv:2506.18919v5 Announce Type: replace-cross Abstract: As a multimodal communication medium that integrates images and text, memes often convey implicit harmful content through metaphors, satire, a
arXiv:2608.22634v1 Announce Type: cross Abstract: Current work on improving reliability in large language model (LLM)- generated answers has primarily leveraged Retrieval-Augmented Generation (RAG), k
arXiv:2608.22619v1 Announce Type: cross Abstract: Generative segmentation provides an alternative to direct pixel-wise prediction by operating on learned latent representations, but effective image-to
arXiv:2510.03536v3 Announce Type: replace-cross Abstract: Multi-turn medical question answering (QA) aims to model realistic clinical diagnosis, where a doctor gathers patient information across multi
arXiv:2608.23302v1 Announce Type: new Abstract: Fashion complementary image generation (CIG) aims to create garments that stylistically match a seed item based on user intent, making it a natural mult
An RLM agent microharness that 'persistently' thinks continuously. What could go wrong :) Introducing Headlong, an open source microharness for persistent agents: self-guided agents that think continu
arXiv:2608.22192v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in persistent social environments, where generated claims can be posted, replied to, remembered, and reused.
arXiv:2606.22342v2 Announce Type: replace Abstract: How does research evolve, and can we trace it at the level of individual claims? Scientific progress is not simply a uniform accumulation of facts.
If you're looking for a weekend project, how about training your own text-to-speech model from scratch on your own GPU, and then running it on any device's CPU? We just open-sourced the entire Pocket
arXiv:2608.23471v1 Announce Type: cross Abstract: Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question:
arXiv:2608.23256v1 Announce Type: new Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reasoni
Hi, since ollama provide multiple cloud models i was wondering is there an app that could be used for chat like claude already has but you can switch models? Or if that is complicated to build at leas
arXiv:2606.14782v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning but incur large KV caches and high decoding latency with lon
arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image i
arXiv:2608.22648v1 Announce Type: cross Abstract: As an increasing number of critical applications, including environmental, emergency, meteorological, and agricultural, rely on real-time anomaly dete
arXiv:2608.23058v1 Announce Type: new Abstract: Large language models (LLMs) now support forecasting systems that combine language-based reasoning with temporal data, evidence retrieval, external tool
arXiv:2608.22035v1 Announce Type: new Abstract: Robot foundation models have substantially advanced perception and control, but natural human-robot collaboration requires more than executing isolated
arXiv:2608.22167v1 Announce Type: new Abstract: Reinforcement learning (RL) has become an effective way to improve the tool-use ability of large language models (LLMs), but most existing RL frameworks
arXiv:2608.23473v1 Announce Type: cross Abstract: Time series forecasting (TSF) is evolving toward multimodal and agentic settings, yet using foundation models remains uneconomical in resource-constra
arXiv:2608.22642v1 Announce Type: cross Abstract: Despite recent advances in molecular foundation models, several limitations remain, such as chemically invalid augmentations, modality collapse, and i
arXiv:2608.23238v1 Announce Type: new Abstract: We present Mover360, a controllable object manipulation framework for 360{eg} images. Unlike perspective images, 360{eg} images in equirectangular proje
arXiv:2608.21810v1 Announce Type: cross Abstract: Clinical decision-making is inherently experience-driven: physicians progressively refine their reasoning by synthesizing patient history, multimodal
arXiv:2608.21454v1 Announce Type: new Abstract: The same fruit appears in a bunch, unpicked, peeled, bagged in plastic, or sliced on a dish, so automated fruit classification in the wild (AFCW) must a
We have been working on some performance optimisations for Qwen3.8 and other models. The main new feature that we introduced is adaptive speculation for Llama.cpp What is it? MTP and DFlash work well
arXiv:2608.21376v1 Announce Type: cross Abstract: Many NLP tasks require systems to provide attribution in their outputs--i.e. citations to grounding sources. Attribution serves as a bulwark against m
arXiv:2602.16642v4 Announce Type: replace Abstract: Neural Collapse (NC) refers to the emergence of highly symmetric geometric structures in the representations of deep neural networks during the term
arXiv:2608.22039v1 Announce Type: new Abstract: Structure-from-Motion (SfM) is a cornerstone of 3D perception, yet current methods often fail when applied to complex videos involving challenging camer
arXiv:2608.23138v1 Announce Type: cross Abstract: Vision-language-action (VLA) models often expose spatial grounding through autoregressive text coordinates or opaque action tokens, creating brittle i
Perplexity AI announced on August 25 2026 the launch of a “Portable Computer” feature, available immediately to all Perplexity Pro and Max subscribers who are using NVIDIA’s DGX Spark hardware. The se
arXiv:2608.22887v1 Announce Type: new Abstract: Large language models (LLMs) are entering decisions in triage and lending, where task-relevant inference must be distinguished from impermissible proxy
arXiv:2608.21874v1 Announce Type: cross Abstract: Deep learning has achieved strong performance in encrypted traffic classification (ETC), yet its computational cost limits deployment on resource-cons
arXiv:2608.23468v1 Announce Type: new Abstract: Anomaly detection is often applied to data stored in relational databases, yet most existing methods require flattening multiple tables into a single fe
arXiv:2608.21482v1 Announce Type: cross Abstract: Background: Multimodal fracture classifiers may benefit from patient and anatomical metadata, but they can also become brittle when contextual informa
arXiv:2608.21815v1 Announce Type: new Abstract: Causal discovery on topological event sequences is crucial for ensuring the reliability of networks. However, existing methods struggle to capture the c
arXiv:2608.21380v1 Announce Type: cross Abstract: With the increased adoption of robotic agents operating in human environments by scanning and sharing 3D representations (e.g., for fleet learning, cl
arXiv:2608.22676v1 Announce Type: new Abstract: Robustness to a bad tool return means answering it in the way that return calls for, which depends on how the tool went wrong. A tool that has failed an
TL;DR - A ~4M example, ~3B token CoT dataset designed around helping small models think more concisely, accurately and reliably. Hi all! For the past few months I have been working on a dataset design
arXiv:2608.22597v1 Announce Type: cross Abstract: Subsampling is effective in tackling computational challenges for massive data with rare events. Overly aggressive subsampling may adversely affect es
arXiv:2608.21375v1 Announce Type: new Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases, vector stores, and graph
arXiv:2608.21610v1 Announce Type: new Abstract: Retrieval-augmented generation relies mostly on flat, fixed-granularity indexes: documents are cut into uniform chunks and retrieved by similarity, disc
arXiv:2608.21636v1 Announce Type: new Abstract: Video Object-Centric Learning (OCL) has traditionally focused on refining the encoder architecture to ensure temporal consistency. In this paper, we arg
Skild AI: Skild AI unveils S1, a robotics foundation model that it says can learn tasks never seen during pretraining, using a single video demo, without fine-tuning — UNSEEN TASKS10-MINUTE HORIZONSON
arXiv:2512.04529v3 Announce Type: replace Abstract: Creating presentation slides from scientific papers is not simply a matter of summarizing paragraphs. A presenter is required to decide what story t
arXiv:2608.21449v1 Announce Type: new Abstract: Time series arise in a wide range of application domains and are analyzed using machine learning in decision-critical settings. Time series classificati
arXiv:2608.21409v1 Announce Type: cross Abstract: In medicine, claims remain valid when supported by empirical evidence grounded in stable biological reality. In law, by contrast, truth is contingent,
arXiv:2608.22594v1 Announce Type: new Abstract: Tabular foundation models (TFMs) have recently emerged as a promising paradigm for machine learning on tabular data, offering the ability to generalize
arXiv:2608.22622v1 Announce Type: cross Abstract: Clinical decision-making relies on identifying relevant patient information to guide diagnosis and treatment, a challenge that is especially difficult
arXiv:2507.18061v4 Announce Type: replace-cross Abstract: Spoken Language Models (SLMs) are expected to support natural spoken interaction beyond task completion. However, existing SLM benchmarks prim
arXiv:2608.22007v1 Announce Type: cross Abstract: The components of a transformer communicate by writing to and reading from a shared residual stream, and mechanistic interpretability has mapped these
arXiv:2411.06039v2 Announce Type: replace Abstract: Despite obesity being widely discussed in the social sciences, the effect of a robot's perceived obesity level on trust is not covered by the field
Today we’re launching Portable Computer on @NVIDIA DGX Spark. Portable Computer is a fully local version of Perplexity Computer, where the entire runtime: orchestrator LLM, subagent LLM, agent harness
arXiv:2501.13976v2 Announce Type: replace-cross Abstract: The prevalence of harmful content on social media platforms poses significant risks to users and society, necessitating more effective and sca
arXiv:2608.22341v1 Announce Type: cross Abstract: Lifting 3D hand poses from 2D monocular representations remains challenging due to the limited availability of large-scale, diverse 3D-annotated hand
arXiv:2608.22081v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enables large language models to incorporate external knowledge during generation, improving factual grounding an
arXiv:2608.23221v1 Announce Type: cross Abstract: Historical retrieval for time-series prediction commonly treats past similarity as a proxy for usefulness. We ask a different question: which historic
arXiv:2608.22591v1 Announce Type: new Abstract: Robot policies receive heterogeneous observations at each decision step, yet sequence models differ in how they organize these inputs over time. We intr