Knowledge catalogue
arXiv:2607.22314v1 Announce Type: new Abstract: Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoida
arXiv:2607.22087v1 Announce Type: new Abstract: Generalization remains a critical bottleneck in AI-generated image detection. Because many modern generators are proprietary or adversarially modified,
arXiv:2607.22436v1 Announce Type: cross Abstract: This work addresses the generation of theoretical correlation matrices with prescribed sparsity patterns associated to graph structures. We propose a
Happy to have @FireworksAI_HQ as our day0 launch partner and bring Kimi K3 to more developers. With Fireworks, you can now deploy and fine-tune the 2.8T Kimi K3 model with just a few clicks! Kimi K3 i
arXiv:2607.21981v1 Announce Type: new Abstract: Chain-of-thought prompting improves language-model reasoning by carrying intermediate states across successive computation steps. However, relying on na
arXiv:2607.22172v1 Announce Type: new Abstract: Accurate yet low-latency depth is essential for radar-camera perception in autonomous systems. Cameras provide rich appearance but lack metric scale, wh
arXiv:2607.22215v1 Announce Type: new Abstract: In this study, we introduce latent PDE mapping, a broadly applicable physics-informed learning technique designed to enable efficient geometric generali
arXiv:2607.21936v1 Announce Type: new Abstract: Historical documents act as invaluable knowledge archives but often suffer from illegibility due to physical deterioration and damage. While existing re
NVIDIA’s Nemotron 3 Ultra, when paired with the ACE‑RTL agent, achieves a 97.1 % average pass rate on the CVDP benchmark across nine RTL task categories—surpassing GLM 5.2 and Kimi K2.6 while using up
arXiv:2607.22226v1 Announce Type: new Abstract: Foundation-model-based vision-language navigation (VLN) has advanced autonomous robot navigation by enabling robots to interpret natural-language instru
arXiv:2607.21665v1 Announce Type: new Abstract: Proactive service assurance in O-RAN requires predicting per-slice SLA violations before they occur. The prediction model must be auditable by operators
arXiv:2607.22225v1 Announce Type: new Abstract: Safe autonomous navigation in shared environments requires the ability to anticipate and react to the latent behaviors of surrounding robots. In this pa
arXiv:2607.21850v1 Announce Type: new Abstract: As semiconductor manufacturing advances toward sub-2nm nodes, local place-and-route (P&R) design-rule violation (DRV) fixing is increasingly limited by
arXiv:2607.22043v1 Announce Type: new Abstract: Although large language models (LLMs) exhibit remarkable reasoning capabilities, their reliance on text-only pre-training restricts the perception of th
arXiv:2607.22534v1 Announce Type: new Abstract: Geometry Foundation Models (GFMs) have substantially advanced monocular 3D reconstruction, yet extending this capability to 4D dynamic understanding rem
**Summary:** Kimi K3 is a publicly available 3‑trillion‑parameter language model now live on Fireworks, offering 1 million-token context windows with native vision and reasoning that rivals top closed
arXiv:2607.21971v1 Announce Type: cross Abstract: Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We h
arXiv:2607.22231v1 Announce Type: new Abstract: Video super-resolution (VSR) using large-scale Diffusion Transformer (DiT) priors achieves exceptional perceptual quality but is often impractical due t
We've open-sourced MoonEP, our high-performance communication library for distributed MoE workloads. Built to make expert-parallel communication more efficient at scale, MoonEP helps reduce communicat
I am writing a fairly complex C++ windows MFC application. I have a few 3090s and can run F16 Qwen3.6-27B with 256K context and MTP. The quality of code is exceptional with this quant vs its lower qua
Most graph-based LLM interfaces use a canvas as a visual layer over what is still a linear chat. I wanted the graph itself to determine what Ollama receives. ThoughtDAG has one rule: wires are the con
Hi everyone, I have a system which I have been using for gaming, R7 5700X, 48GB DDR4, RTX3090 24GB. But I want to use it for Local AI to reduce my reliance on cloud AI providers (mainly usage limits -
AI hardware competition entered a sharper phase this week as Advanced Micro Devices Inc. used its flagship AI event to argue it isn’t merely chasing Nvidia Corp. — it intends to lead the market outrig
everyone is talking about open-weight models. at @huggingface we're invested in open source AI. like, a lot. and more every year. i pulled the public github numbers for our orgs. good excuse to introd
Great to see this out, proud of the team!!! @AMD Instella 16B MoE foundation model, fully open with checkpoint after each stage from pretraining, long-context, SFT, DPO and RL. Dataset detail, trainin
tests done power limiting the GPU on LACT - real power usage varies wildy at 20W it ranges from 25W to 56W same behavior happens on every setting prompt for the test runs: https://github.com/lukesdevl
I've spent the last year or so playing around with open source MLX and GGUF models on iPhone hardware. Given the limitations in memory, GPU/CPU/ANE, and in turn the context window I've been trying to
arXiv:2607.21403v1 Announce Type: new Abstract: Mobile-health interventions increasingly use online learning and decision making algorithms to personalize when to nudge users toward healthier behavior
arXiv:2607.20535v1 Announce Type: cross Abstract: Traditional Predictive Digital Twins often remain geometrically rigid, requiring extensive retraining or fine-tuning whenever the underlying physical
arXiv:2607.09424v3 Announce Type: replace-cross Abstract: We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English
arXiv:2607.20554v1 Announce Type: new Abstract: Reliable and low-latency NR-V2X communications are essential for smart mobility in dense urban environments. However, limited Road-Side Unit (RSU) densi
Maybe Nvidia ultimately won’t win the entire AI enchilada, even as it reminded everyone this week that it offers everything you need to build AI factories. This week, Advanced Micro Devices also annou
Enterprise AI is entering a new phase as organizations shift their focus from experimentation to production deployments that deliver measurable business outcomes. That transition is bringing AI token
arXiv:2607.20439v1 Announce Type: new Abstract: Political evasion is difficult to detect because evasive answers often appear cooperative while avoiding concrete commitment. We present AsymVerify, a c
arXiv:2607.20524v1 Announce Type: new Abstract: Mean cross-positional attention degradation is widely reported in transformer interpretability, yet whether it causally limits contextual retrieval rema
arXiv:2607.21173v1 Announce Type: new Abstract: While automated research systems promise to accelerate empirical analysis, they are prone to silent failures: instances in which analysis code executes
arXiv:2607.20471v1 Announce Type: new Abstract: Personalization, the act of varying a message to induce action from a specific receiver while keeping sender, channel, and time fixed, has a long tradit
arXiv:2607.20950v1 Announce Type: new Abstract: BoN improves model outputs by sampling several candidates and selecting one with a proxy score, but it assumes that complete candidates can be evaluated
arXiv:2607.21076v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) require huge memory and computational costs, which limits their practical deployment. Post-training quantizatio
arXiv:2607.21125v1 Announce Type: new Abstract: Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Exist
arXiv:2607.20852v1 Announce Type: new Abstract: Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitori
arXiv:2607.20561v1 Announce Type: cross Abstract: LoRA adapters provide an efficient way to specialize a pretrained model for many downstream tasks, but deploying one adapter per task requires adapter
arXiv:2607.21407v1 Announce Type: cross Abstract: The boundary and divertor plasma govern how a tokamak exhausts power and particles, setting heat fluxes, target conditions, and the onset of detachmen
arXiv:2607.21243v1 Announce Type: new Abstract: AI-enabled visual perception systems are increasingly deployed in intelligent transportation infrastructure and autonomous vehicle related applications.
arXiv:2607.21185v1 Announce Type: new Abstract: Neurosymbolic (NeSy) systems integrate neural networks with logical reasoning to achieve both generalization and interpretability, but recent work has s
arXiv:2607.20992v1 Announce Type: new Abstract: Trajectory optimization for multi-robot systems remains a critical challenge, particularly when navigating highly non-convex, non-linear, and non-differ
arXiv:2607.21540v1 Announce Type: new Abstract: We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.
arXiv:2607.20692v1 Announce Type: cross Abstract: We present a privacy-preserving framework for synthetic lung CT slice generation developed for the Image-CLEFmed GANs 2026 challenge. The approach com
arXiv:2607.20820v1 Announce Type: new Abstract: Body-based emotion recognition is important for real-time affective systems, but graph-based skeleton models can be computationally expensive. This pape
arXiv:2607.21529v1 Announce Type: cross Abstract: Test-Time Tuning (TTT) on pretrained diffusion models has emerged as a powerful paradigm for video editing. However, there exists a foundational misma
arXiv:2602.10230v2 Announce Type: replace Abstract: Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timest
arXiv:2607.21412v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially i
arXiv:2607.21184v1 Announce Type: new Abstract: Inductive Logic Programming (ILP) originated within the Logic Programming community in the Nineties as a framework for combining symbolic learning with
arXiv:2607.21309v1 Announce Type: new Abstract: Localizing nearby humans and estimating their facing direction are key capabilities for safe navigation and socially aware human-robot interaction. Many
arXiv:2607.20683v1 Announce Type: new Abstract: The sense of touch is central to manipulation, especially when vision is occluded or ambiguous. Although combining vision and touch improves manipulatio
https://github.com/shootthesound/Fizgig Intelligent trainer - Per-image loss tracking with self-adapting training runs — every image gets its own verdict (easy / suspect / stuck / exhausted) and its o
arXiv:2607.21271v1 Announce Type: new Abstract: Equivariant networks embed geometric symmetries as structural priors through weight sharing, achieving remarkable parameter efficiency across vision tas
arXiv:2606.14502v2 Announce Type: replace Abstract: Large Language Models (LLMs) are undergoing a fundamental transformation from conversational generators into integrated AI systems capable of reason
arXiv:2606.17028v2 Announce Type: replace-cross Abstract: Simple linear and frequency-domain models remain surprisingly competitive in long-horizon time-series forecasting, and recent mechanistic evid
arXiv:2607.21130v1 Announce Type: cross Abstract: By leveraging standard RISC-V extensions, namely Zfh (scalar float16) and Zvfh (vector float16), this work proposes an open-source framework to enable