Knowledge catalogue
arXiv:2608.21180v1 Announce Type: cross Abstract: LGE cardiac MRI is widely used for left atrial fibrosis assessment and ablation planning in atrial fibrillation patients as knowledge of fibrotic tiss
arXiv:2608.20494v1 Announce Type: cross Abstract: Multi-agent LLM systems are an emerging networked workload whose rapid deployment raises questions about the traffic patterns they generate. Compared
arXiv:2608.20809v1 Announce Type: cross Abstract: Breast ultrasound diagnosis relies on clinically meaningful semantic concepts, yet most deep learning methods adopt end-to-end image-to-label paradigm
arXiv:2608.20965v1 Announce Type: new Abstract: We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete occurrence, generated result and rela
arXiv:2608.20777v1 Announce Type: new Abstract: As scientific literature grows and papers increasingly under-report limitations, multi-agent LLMs offer a promising approach to systematically uncover t
arXiv:2608.21008v1 Announce Type: new Abstract: Mobile AR frameworks attach a metric pose prior to every casual phone capture, and turning it into reconstruction-grade poses cheaply on CPU is the step
arXiv:2608.21095v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge, but RAG systems usually trust whatever they ret
arXiv:2608.20378v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) is often superficial, relying on refusal mechanisms that trigger only at the final stages of generation
arXiv:2504.09772v3 Announce Type: replace Abstract: Test-Time Scaling has emerged as a powerful method to extend the reasoning capabilities of Large Language Models. However, single-agent TTS faces si
arXiv:2608.20483v1 Announce Type: cross Abstract: We develop analytical and particle-based methods for uncertainty propagation in random neural network models, where both the inputs and network parame
arXiv:2608.21319v1 Announce Type: new Abstract: We formalize the Steiner Traveling Salesman Problem (Steiner-TSP) on Graphs of Convex Sets (GCS), which seeks a minimum-cost closed trajectory through r
arXiv:2608.20918v1 Announce Type: new Abstract: Organizations maintain task-specific adapters for open-weight language models, and each new base-model release forces a migration decision: retain exist
arXiv:2608.20374v1 Announce Type: cross Abstract: How precisely can we tell a language model how to feel? Most work on emotional generation answers with a discrete label - happy, angry, sad - which ca
arXiv:2608.21357v1 Announce Type: new Abstract: In professional life sciences workflows, scientists routinely interpret visual artifacts (gel blots, microscopy images, plasmid maps, flow cytometry plo
arXiv:2608.20740v1 Announce Type: new Abstract: State-of-the-art 3D reconstruction models, whether from visual, range, or both, tend to underperform on thin objects. This is partially due to the small
arXiv:2608.20688v1 Announce Type: new Abstract: The advancement of modern integrated photonics is frequently bottlenecked by device design workflows that rely heavily on manual simulation and expert i
arXiv:2608.21290v1 Announce Type: cross Abstract: We propose VT-MUSE, a Multimodal Unified SEquential representation learning framework for visuotactilemanipulation. Existing approaches often encode v
arXiv:2608.20974v1 Announce Type: cross Abstract: Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent featur
we gave Hermes a phone. it connected over MCP, picked @Uber X, and booked the ride on a real Android device, not an emulator. Claude, Codex, OpenClaw, Cursor all work the same way. Sign-in and your ag
arXiv:2608.20631v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated the ability to solve multi-step tasks requiring planning, tool use, and external information access,
arXiv:2511.13400v3 Announce Type: replace Abstract: We introduce Embedded Stroop, a controlled diagnostic paradigm for measuring image-embedded prompt interference in Multimodal Large Language Models
I'm curious what other people are using for local LLM coding / agentic coding with only 8 GB of VRAM. My current setup is: Intel Core i7-11800H RTX 3070 Laptop, 8 GB VRAM 32 GB DDR4 RAM openSUSE Tumbl
arXiv:2608.21300v1 Announce Type: new Abstract: Foundation models for medical image segmentation, like prompt-based MedSAM, generalize well across domains and modalities, often in zero or few-shot set
arXiv:2511.17886v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder eff
arXiv:2608.20371v1 Announce Type: cross Abstract: A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers for intent detection. We test this claim head-to-
arXiv:2608.21098v1 Announce Type: new Abstract: Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or harm
arXiv:2608.20627v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) interleaves retrieval, reasoning, and answer generation across multiple hops. A retrieval error at hop 1
arXiv:2608.20810v1 Announce Type: cross Abstract: Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, s
arXiv:2608.20400v1 Announce Type: new Abstract: Agentic memory under a fixed budget involves two stages: retention and retrieval. Existing retrieval-centered paradigms implicitly assume necessary evid
arXiv:2608.20345v1 Announce Type: cross Abstract: Conversational AI systems have become informal mental health support resources for Generation Alpha (Gen Alpha, born 2010-2024), with 13.1% of U.S. ad
arXiv:2607.15218v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly serve as high-level planners for embodied agents, where linguistically benign instructions can become unsa
arXiv:2608.21281v1 Announce Type: new Abstract: Recent advances in field technology have led to a massive influx of in-the-wild video data for ecological science. The primary bottleneck in leveraging
arXiv:2606.18847v2 Announce Type: replace Abstract: To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing lon
arXiv:2608.20439v1 Announce Type: new Abstract: Neural PDE operators are increasingly trained on reusable solver archives, yet validation often relies on clean prediction error and parameter-agnostic
arXiv:2608.21049v1 Announce Type: cross Abstract: With the progression in open and disaggregated 6G radio access networks, it is expected that the system will be able to host multi-vendors. In order t
been building ShardFlow for the past few months, a distributed LLM inference framework that splits any HuggingFace transformer across N GPU machines and uses neural speculative decoding to deal with W
A few weeks ago I shared Agent Quest, my open-source experiment that turns Claude Code and Codex sessions into heroes living inside a small 2D world. The original idea was mainly about making it easie
Anthropic’s best AI model struggles to attract users as cheaper tools thrive A few interesting numbers in this FT story gathered from 'people with knowledge of the matter': Anthropic's 'annualized rev
cuda : add POOL_1D support (#27573) cuda : add POOL_1D support fix: add missing trailing newline for editorconfig compliance Website: https://llama.app Attestations: https://github.com/ggml-org/llama.
vendor : update subprocess.h (#27409) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42402532 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a
DeepseekV4: fix rollback with multi-seq (#26756) DeepseekV4: fix rollback with multi-seq fix model loading make pending rollback single use only clear cache for seq_id for full load add assert for com
common : skip device_info loop if it's not going to be printed (#26692) The device_info loop iterates over the discovered devices and gets the available and total memory counts. With the CUDA backend
server : add LLAMA_SERVER_SLOTS_N_DIFF (#27600) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42423433 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple
mtmd: use pillow-accurate algo, correct resize_algo for all models (#27594) mtmd: use pillow-accurate resize algo, correct resize_algo for all models speed optimization Website: https://llama.app Atte
test: move tools/parser to tests (#27548) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42442638 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silico
model : support MTP in GLM-4.5-Air (#26534) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/42447665 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sili
Below @sama is saying that he was wrong on how quickly people would adopt AI, but not admitting that he was wrong about how soon AGI would come. But he was. He literally said in January 2025 that he w
WARNING: I think I made a mistake with omlx, and its results below seem to be without any kind of acceleration. I am rerunning them with Lightning MTP and ANE support for prefill. Will update the post
I haven't had a lot of luck in the reliability of the output of any models so far for local coding use, and find myself relying on Claude's limited free sessions to assist with coding. My coding appli
This is something I've noticed. Back when GLM 5.2 and Kimi K3 launched, there was a media push on pushing how dangerous open source models are. We know why they were doing this; these open models are
I don't know about you guys, but Deep-seek harness is insane. It's not focused on being a coder agent, it's webUI made it very easy to just checkin from time to time, and the best part? Why it's bette
This is one more vibe slopped custom optimization for, in this case, my hardware (m2 ultra 60 cores, 192gb). It is just a fork from llama.cpp with a few changes, it achieves: - DeepSeek V4 Flash, no k
I've tried a few Gemma 4 models, for example 'gemma4:26b-mlx'. It says 'I cannot process images.'. On their website it mentions images, audio etc. https://ollama.com/library/gemma4/tags I’m using Olla
I'm running Qwen 3.8 27B locally on a single GPU. I can push the context to 131k, but I'd rather run it faster at 64k if the agent can manage context properly. What I have in mind is pretty simple: on
Heard a crazy stat the other day. Video generation represents around 70% of the share of AI token consumption in China. A combination of short form content and robotics. In China, video models are gro
Gemma 12B is obviously a very well trained model, I always thought the fine tuning they did on it wasn't really cut out for agentic coding. From my own experiences it struggles to use the tools it's g
I guess children needlessly dying of a disease that has long been fully preventable is a small price to pay for Byron Donalds to become governor of Florida. Brennan: 'Nearly all of Florida is below th
What I ran: 8x B300 on Modal, 56.79 per hour, vLLM, tensor parallel 8, native MXFP4 Cold boot ~27 min (1.56 TB load, JIT, 51 CUDA graph captures) TTFT 0.92 to 1.02 s, decode 92 tok/s steady, 83 tok/s
My setup: RX 6700 XT 12GB i5-11400F 16GB RAM Ubuntu 26.04 ROCm/TheRock + llama.cpp I've spent the last few months experimenting with different backends, quantization, CPU/GPU split, KV cache, batch si
If you maintain an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers traced 94K development events across 557 agentic coding sessions, plus 690K file-level change record