Knowledge catalogue
arXiv:2608.10385v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assess
arXiv:2608.10589v1 Announce Type: cross Abstract: This paper presents pi-SUB, a physics-informed framework for generating synthetic underwater benchmark datasets that bridges the synthetic-to-real gap
arXiv:2608.10288v1 Announce Type: cross Abstract: The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bili
arXiv:2405.03728v3 Announce Type: replace-cross Abstract: Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or
arXiv:2608.11149v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in storing and recalling rich person-related knowledge, raising incre
arXiv:2608.10699v1 Announce Type: cross Abstract: Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-
arXiv:2608.10989v1 Announce Type: cross Abstract: Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with differe
Google DeepMind’s new sign‑language‑to‑text (SL2T) model powers real‑time sign-to-text dictation in Gboard and Live Transcribe on Pixel 11, currently supporting American Sign Language to English. The
arXiv:2608.10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory c
But then users start to report a weird bug. It's the 4th time your team has been trying to fix it. I mean... asking AI to fix it. Unfortunately, it seems like not even Fable can figure it out. You go
i was hoping they would release both today but the big one just dropped now , and it says its been listed since 5 hours ago on huggingface. I guess the real date for 27b is https://modelscope.cn/model
Muse Glimmer 30B feels significantly more precise and reliable, it almost never drops the ball or breaks rules. However, its designs lack creative depth and richness. Qwen3.6 35B, on the other hand, i
Qwen3.8-2.4T-A95B is now live on Fireworks with Day-0 support! This 2.4T parameter MoE model is built for autonomous agents, heavy coding, large context windows, and is ideal for coding and agentic pe
The Qwen Team has released its flagship model, Qwen3.8‑2.4T‑A95B, on the Together AI platform (togethercompute) as of August 12 2026. This 2.4‑trillion‑parameter model is engineered for coding tasks a
Qwen3.8-Max is live on Together AI on day zero. Proud to have supported early testing alongside @Alibaba_Qwen, @vllm_project, and Inferact to get day-zero support live. We’re continuing to optimize pe
arXiv:2608.10963v1 Announce Type: new Abstract: We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a bud
arXiv:2608.10420v1 Announce Type: new Abstract: Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts. A recent framework of
arXiv:2608.10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interact
arXiv:2608.10812v1 Announce Type: cross Abstract: We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiL
arXiv:2608.10549v1 Announce Type: new Abstract: Achieving high accuracy in laser-based cutting of optical films requires careful tuning of parameters such as focal length and laser power beam, adjuste
arXiv:2608.10970v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, maki
arXiv:2608.11045v1 Announce Type: cross Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (
arXiv:2608.09971v1 Announce Type: cross Abstract: Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has produced deterministic models whose medium-
arXiv:2608.10725v1 Announce Type: new Abstract: Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models
arXiv:2608.10524v1 Announce Type: cross Abstract: Driven by the rapid advancement of vision-language representation learning, Text-based Image Retrieval (TBIR) has made notable progress. However, exis
arXiv:2608.10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization proced
I also have 64 gb ddr4 ryzen 5600 Using llama.cpp Ubuntu distro Settings are as follows --n-gpu-layers 999 --n-cpu-moe 36 --no-mmap -ctk q8_0 -ctv q8_0 -fa 1 -c 9000 So rebuilt my llama.cpp build to r
arXiv:2608.11142v1 Announce Type: new Abstract: Agricultural monitoring faces unique challenges, arising from the landscape's complex temporal, phenological, and climate dynamics, yet monitoring them
arXiv:2608.10670v1 Announce Type: new Abstract: At corpus sizes typical of low-resource dialects, single-run comparisons can yield gains that do not replicate. We show this for Garhwali, an under-reso
arXiv:2608.10144v1 Announce Type: new Abstract: We consider federated parameter efficient fine-tuning of large neural networks with low-rank adaptation (LoRA,~Hu et al. 2022). Combining LoRA with fede
arXiv:2607.15606v2 Announce Type: replace Abstract: Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and data-driven research, but evaluating their fidelity
Alibaba released the open‑weights Qwen3.8‑2.4T‑A95B (Qwen3.8‑Max), a fine‑grained mixture‑of‑experts model with 2.4 trillion parameters, hybrid full‑ and linear‑attention, a one‑million‑token context
arXiv:2604.03337v2 Announce Type: replace Abstract: Genotype-environment (GxE) interactions can influence the performance of genotypes across diverse environments, limiting the reliability of genotype
arXiv:2607.16943v2 Announce Type: replace Abstract: Safety validation at signalized intersections remains a critical bottleneck for the deployment of autonomous driving systems (ADS), as these scenari
arXiv:2602.13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences. Progress is limited by a data
arXiv:2608.10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual cont
Kenrick Cai / Reuters: Sources detail moves behind Google's AI reshuffle; Sergey Brin urged key staff to go all in on Gemini, and some teams shifted from DeepMind to corporate Google — Google co-found
SPACEXAI: Grok 4.6 leads on the two strongest knowledge-work / real-world productivity benchmarks (GDPVal-AA and AA-Briefcase) and on the legal benchmark, while remaining highly competitive on coding-
Speaking of fine-tuning, we’ve got support on @axolotl_ai. Start training North Micro Vision right away, no hardware required. Find their docs here: https://docs.axolotl.ai/docs/models/cohere-north-mi
arXiv:2608.10692v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across
arXiv:2608.11075v1 Announce Type: new Abstract: Event cameras capture intensity changes asynchronously with high temporal resolution, requiring novel preprocessing methods for downstream tasks. Unlike
arXiv:2608.10439v1 Announce Type: new Abstract: Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous vide
arXiv:2608.10810v1 Announce Type: cross Abstract: Emotion understanding in discourse requires reasoning beyond surface sentiment because speakers often convey affect through indirect, implicit, polite
arXiv:2608.10837v1 Announce Type: cross Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs. Distilling models into task-specific architectures
arXiv:2608.10258v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do
arXiv:2606.16188v2 Announce Type: replace Abstract: Diffusion models excel in Real-World Image Super-Resolution (Real-ISR) due to their powerful generative priors but suffer from slow iterative sampli
arXiv:2509.25143v2 Announce Type: replace-cross Abstract: Existing medical reasoning benchmarks for vision-language models primarily focus on analyzing a patient's condition based on an image from a s
arXiv:2608.10932v1 Announce Type: cross Abstract: Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimoda
arXiv:2608.11191v1 Announce Type: cross Abstract: GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ab
Ran the model with quants (Q5) and MTP by bartowski with llama.cpp server. It takes ~24GB ram running on M5 Pro with 48GB at about 65t/s. On some tasks it was quite the overthinker. Overall, the quali
arXiv:2608.10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached o
arXiv:2505.11635v2 Announce Type: cross Abstract: Many real-world tasks, from associative memory to symbolic reasoning, benefit from discrete, structured representations that standard continuous laten
The model punches above its weight, outperforming Gemma 4 E2B and Ministral 3 3B across a broad range of visual understanding benchmarks and delivers particularly strong results on document understand
The most dangerous document extraction failure isn't a wrong value. It's a missing row that looks like nothing is wrong. We released ExtractBench yesterday: 370 enterprise docs, 14 systems. The hardes
arXiv:2608.09941v1 Announce Type: new Abstract: While 4-bit weight quantization is critical for deploying Small Language Models (SLMs) on edge devices, evaluations of the resulting performance degrada
arXiv:2606.15821v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, fo
Today, we’re adding another member to our model family. Meet North Micro Vision. Our smallest vision-language model yet, ideal for sophisticated document understanding. Available open-source under an
arXiv:2608.10268v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exis
arXiv:2608.10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predi
arXiv:2608.10346v1 Announce Type: cross Abstract: Although advancements in face landmark detection (FLD) methods continue to push performance boundaries, they overlook two major functional limitations