Knowledge catalogue
arXiv:2602.01995v2 Announce Type: replace Abstract: Conversational diagnosis requires multi-turn history-taking, where an agent asks clarifying questions to refine differential diagnoses under incompl
Today we’re open-sourcing Lily, the local inference engine we built for hybrid compute in Perplexity Computer. Lily is specialized for Qwen3.6-35B-A3B on Apple silicon, built so on-device compute does
arXiv:2609.00832v1 Announce Type: new Abstract: The exponential growth of scientific publications calls for automatic Information Extraction (IE) systems to support knowledge discovery. In this contex
arXiv:2609.01598v1 Announce Type: new Abstract: Accurate segmentation of vascular structures in digital subtraction angiography (DSA) images remains challenging due to the thin, elongated, and branchi
arXiv:2609.00921v1 Announce Type: new Abstract: Personalized Large Language Models (PLLMs) aim to tailor responses to individual users, where a central challenge is preference reasoning: inferring que
arXiv:2609.00830v1 Announce Type: cross Abstract: Whether attention weights faithfully reflect model reasoning has been actively debated in NLP, yet this question remains largely unexplored for the vi
arXiv:2606.21704v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) distillation transfers multi-step reasoning from large reasoning models to smaller students, but verbose teacher traces infla
arXiv:2608.29705v1 Announce Type: cross Abstract: Feed-forward 3D reconstruction models emit a per-pixel confidence that downstream systems read as a reliability signal. It is trained as a loss weight
arXiv:2608.30976v1 Announce Type: new Abstract: Real-world time-series forecasting is rarely a one-shot model invocation: practitioners must formulate tasks, connect data and models, incorporate domai
arXiv:2512.13392v3 Announce Type: replace Abstract: Disocclusion occurs when object movement reveals previously hidden content. Existing image-to-video methods provide different forms of motion and di
arXiv:2608.29831v1 Announce Type: new Abstract: Localizing issue-relevant code regions is a critical step in automated software engineering. However, due to their reliance on sparse trajectory-level s
arXiv:2601.06022v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding b
arXiv:2608.29081v1 Announce Type: new Abstract: Spherical Transformers have emerged as a promising framework for panoramic semantic segmentation (PASS) by operating directly on spherical geometry and
arXiv:2608.29622v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs), yet existing RAG systems often struggle with complex, mu
If you are thinking what model will fit best your HW specs and tasks you are doing here is one table with all currently popular models that still can be considered as local. LLM Test Scores Feature De
arXiv:2608.30929v1 Announce Type: new Abstract: We present a family of retrieval methods for Polish statutory law built on document surrogates: language-model annotations attached to statutory article
arXiv:2603.16138v2 Announce Type: replace-cross Abstract: Generative search systems are increasingly replacing link-based retrieval with AI-generated summaries, yet little is known about how these sys
arXiv:2608.29242v1 Announce Type: new Abstract: Collecting contact-rich robot experiences at scale remains a major bottleneck for generalizable manipulation. Beyond data quantity, robot learning also
arXiv:2608.30618v1 Announce Type: new Abstract: Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the training
arXiv:2608.30092v1 Announce Type: cross Abstract: We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bilingual English-Nepali text, using a custom single-
arXiv:2608.28790v1 Announce Type: cross Abstract: Technical operations teams resolve large volumes of incidents by synthesizing fragmented evidence from ticket text, historical cases, system logs, and
arXiv:2608.30685v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in user-facing services that require iterative tool use under dynamic business conditions. R
arXiv:2608.29111v1 Announce Type: cross Abstract: Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private d
arXiv:2608.31142v1 Announce Type: cross Abstract: The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their u
kv-cells: look up the n-gram history in the sequence position index (#28040) get_prev_tokens() rebuilt a (seq, pos) -> token hash map on every ubatch by walking all used cells, while llama_kv_cells al
arXiv:2608.29206v1 Announce Type: new Abstract: Bias in human-agent interaction can manifest not only through hostile language but also as benevolent bias, whereby unequal treatment hides behind a war
arXiv:2608.28787v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) have primarily been developed for self-supervised representation learning. Denoising JEPA (D-JEPA) rece
arXiv:2508.14323v3 Announce Type: replace Abstract: Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none
arXiv:2608.30256v1 Announce Type: cross Abstract: Logical reasoning with large language models (LLMs) is a critical capability, as it reflects a system's ability to correctly deduce hypotheses from a
arXiv:2510.03136v2 Announce Type: replace Abstract: Confidence calibration, the alignment of a model's predicted confidence with its actual accuracy, is crucial for the reliable deployment of Large La
arXiv:2608.30686v1 Announce Type: cross Abstract: Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity can
arXiv:2608.28699v1 Announce Type: new Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine-
arXiv:2608.28794v1 Announce Type: cross Abstract: Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs
arXiv:2608.29379v1 Announce Type: new Abstract: A language-guided robot operating in a real kitchen must do more than produce a plan that appears correct. It must also execute that plan safely in clut
arXiv:2608.28649v1 Announce Type: cross Abstract: Touchpoint selection in conversion attribution, namely identifying meaningful touchpoints contributing to conversions, is essential for e-commerce rec
arXiv:2608.30922v1 Announce Type: new Abstract: Masked diffusion language models predict tokens from a partially observed response canvas, enabling bidirectional conditioning and parallel token refine
arXiv:2608.30758v1 Announce Type: new Abstract: Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal re
Claude Fable 5.1 tops the Artificial Analysis Intelligence Index but costs 20% more per task than Fable 5 despite a 75% cache read price cut We supported @AnthropicAI with pre-release evaluation of Cl
arXiv:2608.29284v1 Announce Type: new Abstract: Deploying large language models for legal question answering raises challenges that general-purpose leaderboards do not capture, particularly for low-re
arXiv:2608.30183v1 Announce Type: cross Abstract: Lightweight channel attention mechanisms are widely used in image classification, yet their effectiveness in fine-grained visual recognition (FGVR) re
arXiv:2608.30768v1 Announce Type: new Abstract: Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved enco
arXiv:2601.12208v2 Announce Type: replace Abstract: Evaluating conversational systems in multi-turn settings remains a fundamental challenge. Conventional pipelines typically rely on manually defined
arXiv:2608.30023v1 Announce Type: cross Abstract: Generative engines such as ChatGPT, Gemini, and Perplexity answer buyer questions directly and name a shortlist of brands inside the answer. Studying
arXiv:2608.30543v1 Announce Type: new Abstract: Large Language Models (LLMs) offer new possibilities for scaling qualitative analysis, but existing applications often provide limited methodological tr
arXiv:2608.29646v1 Announce Type: new Abstract: Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable to
arXiv:2601.18486v3 Announce Type: replace Abstract: Demographic cue-based evaluation is widely used to study how large language models (LLMs) adapt their responses to signaled demographic attributes w
arXiv:2608.30532v1 Announce Type: new Abstract: Existing approaches for synthesizing Partial Differential Equation (PDE) solvers predominantly rely on autoregressive models, yet their global left-to-r
arXiv:2608.29997v1 Announce Type: new Abstract: We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete diff
arXiv:2608.28615v1 Announce Type: cross Abstract: Synthetic personas based on large language models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet systematic validat
arXiv:2608.28590v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown promise for automating data-science workflows, yet their end-to-end performance depends critically on the a
arXiv:2601.16690v2 Announce Type: replace Abstract: We introduce EMemBench, a programmatic benchmark generator for evaluating long-term episodic memory of agents through interactive games. Rather than
arXiv:2608.28678v1 Announce Type: new Abstract: Scalable Vector Graphics (SVGs) power much of the modern visual ecosystem, yet state-of-the-art generative models focus almost entirely on rasterized im
arXiv:2510.26861v4 Announce Type: replace-cross Abstract: Multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the query. In practic
arXiv:2608.29835v1 Announce Type: new Abstract: Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central f
arXiv:2608.28820v1 Announce Type: new Abstract: Computational pathology (CompPath) is transforming medicine by leveraging artificial intelligence (AI) algorithms to support diagnosis, prognosis, and t
arXiv:2608.30869v1 Announce Type: cross Abstract: Let rgeq3 be fixed, and let mathbf{G}_n be the set of all simple graphs with vertex set [n]={1,ldots,n}. We consider an exponential random graph model
arXiv:2608.30458v1 Announce Type: new Abstract: Accurate bladder tumor segmentation and assessment of mus- cle invasion from T2-weighted MRI are important for treatment plan- ning, but developing robu
arXiv:2601.10015v2 Announce Type: replace Abstract: Personalized Federated Learning (PFL) excels at tailoring client-specific models, which is particularly critical for decentralized and heterogeneous
arXiv:2608.28687v1 Announce Type: new Abstract: Generative models have significantly improved the performance ceiling of image lossy compression at low bitrates by exploiting learned priors. However,
arXiv:2608.29814v1 Announce Type: new Abstract: Modern video generators excel at synthesizing individual clips, but complete video production requires coordinating a long sequence of interdependent cr