Knowledge catalogue
arXiv:2608.28695v1 Announce Type: new Abstract: Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this ato
arXiv:2608.29936v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) degrades across languages, yet the internal mechanism driving this asymmetry remains poorly understood.
arXiv:2608.29327v1 Announce Type: new Abstract: Large language models deployed in specialized domains must improve in-domain performance without sacrificing general capabilities. Existing parameter-ef
arXiv:2608.31068v1 Announce Type: new Abstract: When a large language model fails a reasoning task, it is often assumed to lack the underlying capability. However, this conflates a genuine absence of
arXiv:2608.28339v1 Announce Type: new Abstract: Artificial intelligence can classify artistic styles and synthesize images, but it still lacks a model of the visual language that gives art meaning. Ab
arXiv:2608.27460v1 Announce Type: new Abstract: Large output embedding matrices create a significant memory bandwidth bottleneck during autoregressive decoding, especially for compact LLMs with large
AVX2: Speed up large batch size prompt processing of IQ models (#27402) Batched gemm for grid IQ quants Style updates and a bit more performance Clean up comments Move code around Vectorize IQ panel d
arXiv:2608.27715v1 Announce Type: new Abstract: Federated learning systems are increasingly deployed to facilitate collaborative model training across a heterogeneous client population. Existing pract
arXiv:2608.28266v1 Announce Type: new Abstract: Agent systems powered by multimodal large language models (MLLMs) have advanced rapidly in recent years, yet existing embodied-agent benchmarks still la
arXiv:2608.28080v1 Announce Type: new Abstract: Image-conditioned 3D generation has advanced rapidly, yet existing evaluation protocols largely judge rendered-view plausibility and semantic alignment,
arXiv:2608.27516v1 Announce Type: cross Abstract: Deep learning's diagnostic utility in pathology is constrained by model vulnerability to real-world data imperfections. While current strategies favor
I'm very happy with Qwen-3.8-27B, I run it on my work machine and switched for major part of real coding tasks from cloud subscriptions to it. I use one dedicated headless RTX 3090, and get maybe 1000
arXiv:2608.28361v1 Announce Type: cross Abstract: Machine Unlearning methods for Large Language Models typically assume pre-specified forget and retain sets. In realistic settings, however, requests m
arXiv:2608.28134v1 Announce Type: new Abstract: Reliable long-horizon time series forecasting is an important yet difficult problem. Trends and seasonality introduce complex temporal structure that ch
Linux just got a local AI upgrade. 🐧 Congrats to @lmstudio on bringing Bionic to Linux, making it even easier to run local agents and open models on NVIDIA hardware. Bionic is now available for Linux!
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.
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:2608.28378v1 Announce Type: new Abstract: Large language models are increasingly used as agentic workflow executors, yet existing training data and benchmarks largely assume informationally comp
arXiv:2608.27704v1 Announce Type: new Abstract: When machine learning classifiers are retrained, inputs correctly classified by the previous model version may be misclassified by the updated version,
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:2608.28444v1 Announce Type: new Abstract: Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new token costs more than the previous
The First Golden Age of AI writing is now over. For a brief period of time, many people were better off having Claude do a lot of their writing, because it is a pretty good writer & AI detectors were
arXiv:2608.28518v1 Announce Type: cross Abstract: We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that
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
We used HFlow to evaluate the latest open weights VLMs for processing egocentric data. This was based on Build AI's Egocentric-10k evaluation, which used Gemini 2.5 Flash to measure hand visibility an
I got a 50% performance boost (20 t/s -> 30 t/s) in llama.cpp for MoE models that don’t fit entirely in VRAM—in my case, Qwen 3.8 Flash Next. The idea is simple: instead of offloading entire layers to
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
GLM 5.3 and GLM 5.3 Flash (previously Ox Alpha) are fully rolled out on Ollama's cloud. Private. Fast. US and Europe hosted. Zero data retention. GLM 5.3: ollama launch claude --model glm-5.3:cloud GL
I have a 2 DGX Spark setup recently and I have been happily running Deepseek V4 Flash 0731. Since the release of GLM5.3 Flash and Qwen 3.8 Flash Next this week, a lot of folks are still waiting to see
Folks! We're just 50 PRs away from more faster inference. Hopefully by end of year. Experts!, please chip in there. List of Open/Ongoing PRs(and also Discussions) related to CPU/RAM/Disk/Hybrid: [Disc
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
this model is really something incredible, saved us like 600 dollars. my fiance is always breaking her electronics and then getting me to fix them. The other day she brought me her phone and it was st
This base model is only 43m parameters trained on 3m arXiv abstracts. We plan to continue pre-training and post training. If you create fine-tuning datasets or if you know of any datasets that can hel
arXiv:2608.26469v1 Announce Type: new Abstract: In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter incr
arXiv:2507.11515v2 Announce Type: replace-cross Abstract: Operating Large Language Models (LLMs) on edge devices is increasingly challenged by limited communication bandwidth and strained computationa
arXiv:2608.26992v1 Announce Type: new Abstract: Representation learning has attracted great atten- tion and managed to reach good performances as a pretraining method for downstream tasks or as a firs
arXiv:2608.27038v1 Announce Type: new Abstract: Although batch prompting makes large language model inference more efficient by processing multiple instances simultaneously, it suffers from unpredicta
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
Perplexity AI has released its new language model GLM 5.3 on Perplexity Computer. Designed for long‑context, multimodal agent workloads, GLM 5.3 outperformed the previous GLM 5.2 on the company’s WAND
arXiv:2608.27241v1 Announce Type: new Abstract: Computationally demanding and opaque deep learning models can be better understood and optimized by analyzing how they transform data. While deep transf
arXiv:2606.21891v2 Announce Type: replace Abstract: Scientific discovery can be formulated as an iterative search process over the space of hypotheses and experiments. Contemporary methods navigate th
arXiv:2608.26489v1 Announce Type: new Abstract: Detecting woody clearing is vital for managing biodiversity. Deep learning models can detect change in woody vegetation from bitemporal remote sensing i
arXiv:2608.26714v1 Announce Type: cross Abstract: Diffusion-based Video Virtual Try-On (VVT) achieves high visual fidelity through bidirectional spatio-temporal modeling, but complete-clip dependence
arXiv:2608.26820v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) exhibit strong generalization, visual instruction tuning for downstream tasks inevitably causes catastrop
arXiv:2509.07274v4 Announce Type: replace Abstract: Migration has been a core topic in German political debate, from postwar expellee displacement to labor migration and recent refugee movements. Larg
arXiv:2608.26283v1 Announce Type: cross Abstract: Extracting a shared set of unknown, not directly measurable quantities from multiple, heterogeneous datasets is a common challenge across scientific d
arXiv:2608.26535v1 Announce Type: new Abstract: Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditioning, where text, images, audio, and video can jointly s
arXiv:2608.26292v1 Announce Type: cross Abstract: Every memory-based knowledge editor in the SERAC lineage depends on a scope decision: given a query, does a stored edit apply? We report that current
arXiv:2608.27206v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) demonstrate exceptional visual reasoning capabilities, yet their inference costs escalate rapidly with the proliferation
arXiv:2608.26720v1 Announce Type: new Abstract: Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previo
arXiv:2608.26324v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward h
arXiv:2608.27205v1 Announce Type: new Abstract: Nitrogen rates for winter wheat are set before the season, under unknown prices and weather. The standard UK advice does not respond to prices, yet rece
arXiv:2608.27302v1 Announce Type: new Abstract: Accurate identification of the correct view or angle in cardiac ultrasound (echocardiogram) is a critical component of cardiologic imaging. This step is
arXiv:2608.26136v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose language-model activations into sparse, interpretable features, and an appealing way to aim them at reasoning is to
arXiv:2608.26159v1 Announce Type: cross Abstract: Self-Generated Text Recognition (SGTR)--the ability of an LLM to identify its own outputs--poses risks to AI safeguards that rely on LLMs as evaluator
arXiv:2608.26550v1 Announce Type: new Abstract: Reinforcement learning-based knowledge distillation has the potential to transfer complex reasoning from teacher to student models, yet it currently fac
Learn how Salesforce used Amazon SageMaker AI Inference Component placement (the SchedulingConfig parameter) to distribute model copies across multiple Availability Zones, meeting their Multi-AZ high
arXiv:2608.27176v1 Announce Type: cross Abstract: Understanding spoken dialogue requires joint reasoning over lexical content and paralinguistic acoustic signals such as emotion and conversational int
arXiv:2608.25513v1 Announce Type: cross Abstract: Random feature methods provide a scalable approximation to kernel ridge regression (KRR), but the regularization parameter that yields the oracle lear
arXiv:2608.24954v1 Announce Type: new Abstract: Large language models (LLMs) hallucinate numerical values when generating high-stakes meteorological text, posing risks for weather communication. We pr