Knowledge catalogue
arXiv:2608.28113v1 Announce Type: new Abstract: The NVIDIA Blackwell architecture, with native support for the ultra-fine-grained NVFP4 format, opens new opportunities for accelerating large language
I am the product lead for the training platform at @FireworksAI_HQ . Today the Training API and Fireworks Lab are GA. I won’t walk you through all the features. I want to tell you why teams train with
arXiv:2603.18031v2 Announce Type: replace Abstract: Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence mod
arXiv:2608.28435v1 Announce Type: new Abstract: Many robotic tasks are temporally extended and demand precise specifications of subgoals, constraints, and their temporal ordering. Yet human operators
arXiv:2608.28192v1 Announce Type: new Abstract: Spatio-temporal video grounding (STVG) requires models to identify when a referred event occurs and localize the target entity throughout that interval.
The LWiAI Podcast #255 (August 26 2026) reviewed recent AI alerts, including Google’s Gemini 3.7 Flash, Jalapeño’s record‑speed benchmark results, Qwen 3.8, and a case of an entirely AI‑guided drone t
Just ordered a TB5 enclosure plus 4TB SSD to prepare for M5 Ultra 512GB. I am planning to download the following models in advance. Would like to ask the M3 Ultra 512GB owners whether the quants are t
arXiv:2509.26536v3 Announce Type: replace Abstract: We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding r
arXiv:2512.00234v3 Announce Type: replace Abstract: There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. How
arXiv:2608.27816v1 Announce Type: new Abstract: Personalization has attracted growing interest in LLM applications, yet existing retrieval-based approaches depend heavily on retrieval quality and degr
arXiv:2608.28075v1 Announce Type: new Abstract: Manipulation in partially observable environments requires planning under incomplete scene information. In such settings, an initially valid plan may ex
arXiv:2603.28387v3 Announce Type: replace-cross Abstract: Trustworthy clinical AI must use real evidence and avoid relying on surface-level artifacts. We evaluate 12 open-weight vision-language models
Mac Studio, 96GB unified memory (M3 Ultra). I want the largest usable Qwen3.8-Flash-Next setup, and I'd rather not burn 100GB of bandwidth on the wrong download. Here's my math. Please tell me which p
arXiv:2608.28219v1 Announce Type: new Abstract: Cross-identity character animation aims to drive a target identity from a reference image to follow the motion of a source character from a driving vide
arXiv:2608.27831v1 Announce Type: cross Abstract: Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues--long, structured, an
TL;DR - yeah it works, no wild skills or patching required. 37-50 tg/s when generating text, spiking over 60tg/s when writing code and mtp hits hard. Your results can be better if you have a better mo
NVIDIA’s BioNeMo Agent Toolkit integrates over a decade of life‑science models and libraries into agent-callable skills, and when combined with Claude Science and NVIDIA NIM microservices it allows AI
arXiv:2608.28270v1 Announce Type: new Abstract: We present a real-time semantic navigation framework for Unmanned Aerial Vehicles (UAVs) focused on improving time efficiency in the Object Goal Navigat
arXiv:2608.28099v1 Announce Type: cross Abstract: Real-time classification during language model inference is valuable for safety filtering, behavioral analysis, and model monitoring, but current appr
arXiv:2608.27578v1 Announce Type: cross Abstract: Training effective foundation models requires massive and organized datasets, yet scientific domains such as nuclear fusion present unique challenges
arXiv:2608.28216v1 Announce Type: new Abstract: Locating a specific object instance in a cluttered scene using a single reference image and a short description, and reporting when that instance is abs
We’re excited to launch the official LlamaParse connector on Claude! Yes Claude can already read PDFs, and it probably works fine for relatively simple queries over relatively simple docs. But if you
arXiv:2608.27768v1 Announce Type: cross Abstract: A language model with access to tools can commit to a final claim unsupported by the evidence it has seen, even when a single available tool call woul
arXiv:2608.28033v1 Announce Type: new Abstract: Multi-view stereo (MVS) methods typically deliver highly accurate 3D reconstructions from multiple registered RGB images, thanks to the highly informati
11/ METR and Redwood’s work is extremely valuable, but it assesses model behavior and alignment. That is only half the picture. We also need an independent account of how OpenAI’s containment failed.
CUDA: use the fast mm_ids_helper path for any n_expert_used (#27978) The optimized path grouped warp lanes by token and required warp_size % n_expert_used == 0, with a single hardcoded exception paddi
Hey guys I have been working on a open source LLM development repo. Anyone can train any amount of parameter against any arch (GQA, MLA, Dense...) When I tried to implement MLA I read the technical re
I’ve been experimenting with MiniMax H3 and finally have video generation working in TensorSharp. TensorSharp started primarily as a local GGUF/LLM inference engine, so getting a video-generation pipe
Been working really hard for the past month to bring to the community all these models, the hardest was for sure LongCat-Flash-Lite-Sparse who required TONS of work, first I needed to have Heretic sup
specs hardware: M4 Max 128GB Studio inference engine: llama.cpp (qwen4exp branch) judge: claude-opus-4-6 AtomicChat/Qwen3.8-Flash-Next-GGUF Qwen3.8-Flash-Next is a great model I benched in my previous
Hey all, I stumbled onto something funny and figured I'd share before it gets buried. I'd been running the Ornith 1.5 35B A3B GGUF (Q4_K_M) for a while, then recently a new revision showed up in my HF
GLM-5.3-Flash is live on Fireworks on day… 2 Why? Because we take quality very seriously. We found a benchmark discrepancy we couldn’t explain, so we delayed the launch to investigate. Day 0 (Wed): we
happened simultaneously across the board. OpenCode, OpenRouter, and Ollama all ruined DeepSeek at the exact same moment. They literally turned a brilliant model into a complete idiot overnight. I abso
You do not need frontier models for everything. For example, open models are great for automations. If you are not sure where to adopt open models, start there. It's one of the biggest changes I've ma
arXiv:2603.28410v2 Announce Type: replace Abstract: Preference-based many-objective Bayesian optimization typically assumes that all pairwise comparisons arise from a single latent utility function, d
Agent Seer synthesizes graded multi-turn tool-use eval scenarios from MCP specs alone—no examples, live tools, or domain tuning.
arXiv:2608.26133v1 Announce Type: new Abstract: Evaluating AI agents that use external tools requires realistic test scenarios that capture how practitioners compose tools and iterate across conversat
arXiv:2608.26198v1 Announce Type: new Abstract: Operating a scientific instrument such as an atomic force microscope (AFM) requires continuous expert decision-making. A trained user defines the experi
arXiv:2608.26130v1 Announce Type: new Abstract: Coding agents built on large language models (LLMs), such as Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Aider, receive tool responses that r
arXiv:2608.26152v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit unprecedented natural language generation and many text-based problem-solving capabilities. Indeed, in many langu
arXiv:2608.26991v1 Announce Type: new Abstract: Powerful code agents can execute scripts, call tools, and manage files, yet many important applications remain accessible primarily through graphical us
sycl: bind the f16 KV cache in place for the oneDNN SDPA path (#27468) Measured at a live KV length of 34816 (32768 depth plus one 2048 ubatch), on Qwen3.8 27B Q4_K_S: per tensor 4 * 34816 * 256 * 2 B
OpenVINO: Update OV to 2026.3.1, whisper.cpp support, Qwen3.5 on NPU, and new ops (#27843) OpenVINO Backend: Fuse IM2COL + MatMul convolution into OpenVINO convolution ci:ggml-ov: Skip recurrent state
BREAKING: SpaceXAI has released a major new update for Grok Build (v1.0.13). The update improves reliability with automatic retries and recovery from truncated responses, inference failures, oversized
arXiv:2608.27167v1 Announce Type: new Abstract: An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked
arXiv:2608.26386v1 Announce Type: cross Abstract: Retrieval-augmented methods improve factual accuracy by grounding language models in external knowledge, but retrieving over unstructured text often i
arXiv:2608.27391v1 Announce Type: new Abstract: LLMs are increasingly able to answer complex questions about enterprise-scale document collections. But evaluation is hard: companies don't want to shar
arXiv:2601.04778v2 Announce Type: replace-cross Abstract: Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actio
arXiv:2608.26462v1 Announce Type: cross Abstract: Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly
arXiv:2509.03345v3 Announce Type: replace Abstract: Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of
arXiv:2608.26674v1 Announce Type: cross Abstract: As large language models are increasingly deployed to simulate diverse human characters, ensuring persona fidelity, defined as the extent to which an
arXiv:2608.26153v1 Announce Type: new Abstract: Clinical electroencephalography (EEG) reporting remains largely manual and time-consuming, and current EEG software ecosystems do not produce the struct
arXiv:2608.26154v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into digital health platforms to generate summaries of complex medical data. Although t
arXiv:2608.26310v1 Announce Type: new Abstract: Large language models can now generate complex, multi-step mathematical proofs, but reliably determining their correctness and localizing early logical
arXiv:2608.26746v1 Announce Type: cross Abstract: Generated operational programs are often validated with either a few hand-written examples or exhaustive regression suites. The former can miss sparse
arXiv:2608.24168v2 Announce Type: replace Abstract: A unified audio model must recognize and understand linguistic, paralinguistic, and environmental information while supporting speech synthesis and
arXiv:2608.27384v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are increasingly promising for robotic manipulation, yet their real-world deployment remains bottlenecked by high in
arXiv:2608.26676v1 Announce Type: cross Abstract: Pruning is a practical approach to compress large language models (LLMs), but it can amplify text degeneration, especially repetition loops, even when
arXiv:2608.26950v1 Announce Type: new Abstract: Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing
arXiv:2608.26163v1 Announce Type: cross Abstract: Cough events during live spoken conversations carry clinically valuable respiratory signals, yet existing dialogue systems treat them as acoustic nois