Knowledge catalogue
arXiv:2608.12829v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffus
arXiv:2604.03181v2 Announce Type: replace-cross Abstract: Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing pol
arXiv:2608.13317v1 Announce Type: new Abstract: Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck.
arXiv:2608.13416v1 Announce Type: new Abstract: Humans effortlessly perceive the present while remembering the past, yet streaming VLMs often trade off real-time perception against long-term memory. P
arXiv:2608.13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today
arXiv:2501.14844v3 Announce Type: replace-cross Abstract: Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in
arXiv:2608.13556v1 Announce Type: new Abstract: Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures ha
I prefer the model to have the internet as a source of truth and info and my coding work needs lot of web lookups. The middle bar section ( light blue) is the weekly quota taken by it. 120 web search
arXiv:2510.16898v2 Announce Type: replace-cross Abstract: Accurate prediction of electricity prices is crucial for stakeholders in the energy market, particularly for grid operators, energy producers,
spec : auto-detect mtp draft model type (#27005) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramew
arXiv:2511.20597v2 Announce Type: replace-cross Abstract: The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web applica
arXiv:2608.11343v1 Announce Type: new Abstract: Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder
arXiv:2608.11767v1 Announce Type: new Abstract: When a language model answers an interventional question, the computation it must perform depends on the type of evidence the query requires. We report
arXiv:2608.11555v1 Announce Type: new Abstract: Practitioners enrich customer-return models with ever more signals (lifetime value, category, recency/frequency, calendar, geography), and the temporal-
arXiv:2507.15100v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) determines whether a premise entails, contradicts, or is neutral with respect to a hypothesis. The task is of
arXiv:2608.11249v1 Announce Type: cross Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual data - including pla
arXiv:2502.00837v3 Announce Type: replace-cross Abstract: Natural Language Processing (NLP) is now embedded in critical sectors including healthcare, finance, and customer relationship management, whe
arXiv:2608.11562v1 Announce Type: cross Abstract: Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks. Although single-image
Overview ggml_cpu_fp16_to_fp32 leverages hardware F16C intrinsics (AVX-512, AVX2, etc.), faster than the software-only ggml_fp16_to_fp32_row, bringing 17-31% gain in prompt processing rate for a small
arXiv:2608.12239v1 Announce Type: cross Abstract: Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hi
arXiv:2608.11224v1 Announce Type: new Abstract: Materials research advances through accumulated experience - scripts that work, protocols that are trusted, warnings attached to failed calculations or
arXiv:2608.12035v1 Announce Type: cross Abstract: Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship.
Hey everyone, Non-native speaker, writing my post by hand, let me know if I make mistakes (can only learn from it!) Muse Glimmer 30B is so far quite nice, but I haven't found a clear-cut case yet what
arXiv:2608.11741v1 Announce Type: cross Abstract: The scholarly exegesis of ancient Chinese characters demands integrating visual observation, linguistic analysis, and historical context. However, exi
arXiv:2608.11815v1 Announce Type: cross Abstract: Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models. Beyond perturbation generatio
arXiv:2608.11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC). Existing PIC methods, however, are built for full-attention models, where
arXiv:2608.11616v1 Announce Type: new Abstract: Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to
arXiv:2607.17154v2 Announce Type: replace-cross Abstract: Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it rema
arXiv:2608.11793v1 Announce Type: new Abstract: CAD plan parsing is a fundamental task in Building Information Modeling (BIM), aiming to automatically extract architectural elements including walls, d
On Aug 13 2026, OpenAI announced a preview of its “Ultrafast” mode for the GPT‑5.6 model, called Sol, which claims inference speeds up to 14× faster than current releases. The feature is initially rol
arXiv:2608.11573v1 Announce Type: cross Abstract: Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LL
arXiv:2608.11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks wit
arXiv:2608.11229v1 Announce Type: new Abstract: Comparative feedback, asking people which of two behaviors they prefer, has become a standard way to align robot and agent behavior with human intent wh
arXiv:2608.11238v1 Announce Type: new Abstract: Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence, yet existing evaluation fr
arXiv:2608.11236v1 Announce Type: cross Abstract: Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue
arXiv:2608.11223v1 Announce Type: cross Abstract: Entry-only automatic fare collection systems record boardings but not alightings, preventing direct construction of origin-destination (OD) matrices.
arXiv:2608.12282v1 Announce Type: new Abstract: Agents deployed in enterprise settings must reason across structured APIs and document collections, yet existing benchmarks evaluate these capabilities
arXiv:2602.14419v2 Announce Type: cross Abstract: This paper reformulates Transformer/Attention mechanisms in Large Language Models (LLMs) through measure theory and frequency analysis, theoretically
We’re launching DeepSeek-V4-Pro today! 🚀 🔷 Major Agent upgrades with strong production gains! 🔷 Flexible reasoning effort for V4-Pro & V4-Flash: low for simple tasks, high for daily Agent workflows, m
arXiv:2608.11403v1 Announce Type: new Abstract: Self-consistency (SC) via majority vote is a widely used way to spend inference-time compute: sample N chains of thought, return the plurality answer. O
arXiv:2608.11649v1 Announce Type: new Abstract: As users increasingly turn to Large Language Models (LLMs) for information and advice on political matters, particularly during election periods, the po
arXiv:2608.10760v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has become the de-facto interface for connecting LLM agents to enterprise tools, and adoption has been explosive: wit
arXiv:2608.10588v1 Announce Type: cross Abstract: Purpose: Fine-grained handshape recognition supports computational sign-language transcription, recognition, and translation, but broad, phonetically
arXiv:2608.11173v1 Announce Type: cross Abstract: The attention mechanism forms the foundation of many modern AI models such as the Transformer. In one subclass of problems where attention is used, in
arXiv:2508.03611v3 Announce Type: replace-cross Abstract: This paper presents Astrolabe, a randomized prediction-guided scheduler for one-shot request dispatch in multi-instance large language model (
mtmd: support pocket-tts (#26871) adapt the api text model ok working impl, need verify and clean up mtmd: build the pocket-tts transposed convolutions as GEMM + col2im ggml_conv_transpose_1d has no g
chat : tighten bare function parsing for Qwen models (#26793) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
common: Add CLI > ENV > models-presets > INI precedence CLI flags have the highest precedence ENV vars have the second-highest precedence System and User configs have the lowest precedence Linux/BSD/M
arXiv:2608.10462v1 Announce Type: new Abstract: Large language models (LLMs) are trained on massive and largely undisclosed corpora that may contain copyrighted or privacy-sensitive content. Data cont
arXiv:2608.10690v1 Announce Type: new Abstract: Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus
arXiv:2608.10506v1 Announce Type: cross Abstract: Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resourc
arXiv:2608.10677v1 Announce Type: new Abstract: Professionals across medicine, engineering, finance, manufacturing, and the sciences often make consequential decisions from charts. Existing chart benc
arXiv:2608.10636v1 Announce Type: cross Abstract: Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Pri
arXiv:2608.10433v1 Announce Type: new Abstract: Forecast accuracy does not tell us which past inputs produced a prediction. We separate three questions for time-series models with known delay structur
arXiv:2608.10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed re
arXiv:2608.10181v1 Announce Type: new Abstract: Computer vision saliency models predict where people will look, one map per image, and a billion-dollar predicted-attention industry sells those maps in
arXiv:2608.09938v1 Announce Type: cross Abstract: Hyperelastic deformations are highly sensitive to domain geometry and boundary conditions, making generalization across both a critical capability for
Sometimes you have tasks that are outside of your expertise and the idea is this workflow automation could be leveraged to manage to have local AI figure it out using research from his workflow gather
arXiv:2608.10429v1 Announce Type: new Abstract: Deep learning models that synthesize PET from CT or MRI can reduce patient dose and scanner demand, but are typically optimized with global losses such
arXiv:2608.10688v1 Announce Type: new Abstract: Purpose: Keyphrases are statistically and semantically important textual units that can also attract readers' attention during comprehension. However, e