Knowledge catalogue
arXiv:2608.00515v1 Announce Type: cross Abstract: Large language model tutors can be correct and helpful yet disclose an answer or decisive reasoning before that disclosure is authorized. We formalize
arXiv:2608.00077v1 Announce Type: new Abstract: Visual-token pruning is usually judged by answer quality at a fixed retention budget. For text-rich multimodal large language models (MLLMs), this proto
arXiv:2608.00207v1 Announce Type: new Abstract: Large Language Models (LLMs) perform strongly in English medical tasks but degrade substantially in Arabic, a gap widely attributed to limited training
arXiv:2608.01014v1 Announce Type: new Abstract: Preference optimization improves mathematical reasoning in large language models (LLMs), but reliable chosen-rejected pairs usually require verified ans
arXiv:2608.02222v1 Announce Type: new Abstract: One-shot federated learning (OSFL) has emerged as a promising collaborative model learning framework with only a single round of communication, offering
arXiv:2607.16898v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) have recently demonstrated powerful instruction-based image editing capabilities, while also raising serious
I run my inference machine in the living room, so noise and heat output are a significant concern. Ran a quick test using my daily driver model (Qwen 3.6-27b) and at 480W, the card outputs only 2.1% l
arXiv:2608.00118v1 Announce Type: cross Abstract: Cybersecurity is a fundamental requirement for protecting wearable devices used in healthcare Internet of Things (H-IoT) systems. Security failures in
arXiv:2608.02112v1 Announce Type: new Abstract: Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking informat
arXiv:2608.02359v1 Announce Type: new Abstract: Attributing quotations to their speakers in literary texts remains an open challenge. Standard methods, which independently predict a speaker mention fo
arXiv:2608.01704v1 Announce Type: cross Abstract: A benchmark score means nothing without knowing what a trivial method achieves and what the best possible method could achieve. We construct both boun
NVIDIA Alpamayo 2 Super is a publicly available 34‑billion‑parameter vision–language–action model that merges a 32‑B Cosmos 3 Super Reasoner with a 2‑B action‑expert diffusion network. It produces uni
arXiv:2608.01633v1 Announce Type: new Abstract: Large language models (LLMs) enable neural architecture search (NAS) directly over executable neural network programs. However, code-level flexibility d
arXiv:2608.01918v1 Announce Type: cross Abstract: Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable
arXiv:2511.20635v3 Announce Type: replace Abstract: Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal cohere
arXiv:2608.00956v1 Announce Type: new Abstract: This paper presents an interpretable machine-learning framework for predicting the splitting strength (ST) of asphalt concrete and supporting data-drive
arXiv:2607.09786v3 Announce Type: replace-cross Abstract: To curb overthinking and reduce inference costs, researchers now train reasoning models with penalties on chain of thought length. We find tha
arXiv:2608.01094v1 Announce Type: new Abstract: Federated learning enables medical-imaging models to be trained across hospitals, and privacy law, most explicitly the GDPR ``right to be forgotten'', t
Released today, with emphasis on agentic capabilities. I really like their models for simple, high volume tasks ('summarize these gazillion documents') and their 8b-a1b was my go-to for certain tasks
arXiv:2608.01662v1 Announce Type: cross Abstract: DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer. However, practical deployment remains constrain
arXiv:2608.01328v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are rapidly evolving with expanded context windows and stronger reasoning capabilities, enabling multi-chart un
arXiv:2603.11804v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for sat
arXiv:2608.02053v1 Announce Type: cross Abstract: Brain tissue microstructure estimation with machine learning provides higher computational efficiency than conventional fitting. However, machine lear
arXiv:2608.00232v1 Announce Type: new Abstract: Surgical augmented reality (AR) can provide contextual guidance by overlaying virtual annotations, tool cues, and procedural information onto the surgic
arXiv:2607.09757v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning enables large language models to adapt to downstream tasks with substantially lower computational and storage cost,
arXiv:2608.00502v1 Announce Type: new Abstract: Affordance grounding aims to localize the functional region for interaction, such as the handle to grasp or the button to press, rather than the whole o
arXiv:2608.01334v1 Announce Type: new Abstract: AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones. In practice, detectors trained on existing data often fail t
arXiv:2509.22992v2 Announce Type: replace Abstract: As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency
arXiv:2608.01743v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central paradigm for large language model (LLM) post-training, but optimization toward new objectives can deg
arXiv:2608.00573v1 Announce Type: cross Abstract: Serving Mixture-of-Experts (MoE) large language models across distributed edge servers is bottlenecked by the cross-server expert transmission. The ex
arXiv:2608.01471v1 Announce Type: new Abstract: Understanding sentiment in low-resource languages remains a key challenge for Natural Language Processing (NLP), particularly when domain-specific data
What's Changed Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically /v1/chat/completions streaming now matches OpenAI's wire format: rol
arXiv:2607.29614v1 Announce Type: cross Abstract: The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI). Ho
arXiv:2607.29539v1 Announce Type: cross Abstract: Standard AI-text detection benchmarks compare human-written text against text generated directly by large language models (LLMs). While prior work has
Qwen from Alibaba has released the Qwen 3.8‑Max model on the Venice platform, enabling users to ask questions anonymously. The announcement encourages users to try the new functionality immediately. T
arXiv:2607.28966v1 Announce Type: new Abstract: Large language models often improve task performance by generating long reasoning traces, but the resulting computation is frequently wasted on redundan
arXiv:2405.07708v3 Announce Type: replace Abstract: Decentralized learning (DL) enables participants to collaboratively train models without a central server, yet it faces significant scalability chal
Businesses want to quickly and safely deploy AI agents to drive revenue, mitigate risk, and optimize capital, all without disrupting mission-critical ERP systems. And to power AI agents, you need more
arXiv:2607.29078v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student
Ran DeepSeek V4-Flash-0731 — the full official checkpoint, not a re-quant — on commodity used hardware. Sharing because I couldn't find anyone else publishing Ampere results for this engine. Why bothe
arXiv:2607.28894v1 Announce Type: new Abstract: Computational cognitive modeling seeks to infer latent cognitive mechanisms underlying observed behavior. Bayesian inverse planning provides a principle
arXiv:2603.27790v2 Announce Type: replace Abstract: We present a lightweight, training-free trajectory correction method that adapts a pretrained image editing model to each input manga image using on
arXiv:2601.22876v2 Announce Type: replace Abstract: Spiking neural networks (SNNs) promise energy-efficient inference for large language models (LLMs), yet most reported savings rely on compute-operat
arXiv:2607.29002v1 Announce Type: new Abstract: Online shoppers increasingly turn to AI shopping assistants, using images and multi-turn dialogue to express and refine product needs that are difficult
arXiv:2607.29545v1 Announce Type: new Abstract: Multimodal video generation aims to generate and edit videos conditioned on arbitrary combinations of text, images, and videos within a single model, al
Has anyone followed nousresearch work on Hermes? I mean we are Q3 2026. We have some crazy models trickling down from HGX territory to multi gpu workstation. And we have nousresearch deploying the 0.2
arXiv:2607.29129v1 Announce Type: new Abstract: Relational Foundation Models (RFMs) require large-scale synthetic relational databases for pretraining, but existing approaches tightly couple data gene
Hey there! So today we're releasing SupraBrain-50M, a hybrid language model that combines Gated DeltaNet linear recurrence with Sliding-Window Attention and Surprise-Gated update mechanisms to deliver
arXiv:2607.28955v1 Announce Type: cross Abstract: AI-generated videos are becoming increasingly realistic and difficult to distinguish from authentic ones, which facilitates malicious misuse and poses
arXiv:2607.28814v1 Announce Type: cross Abstract: In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that
arXiv:2607.29601v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) commonly adapts large language models using a single shared Low-Rank Adapter (LoRA). This shared optimization spa
arXiv:2607.09598v2 Announce Type: replace Abstract: Lightweight speech recognition models are critical for edge deployment, yet highly optimized architectures like Moonshine often fail on morphologica
arXiv:2607.29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential
arXiv:2601.22546v2 Announce Type: replace-cross Abstract: The recent advancements in Large Language Models (LLMs) have attracted interest in exploring their in-context learning abilities and chain-of-
arXiv:2607.28648v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for emotional support tasks, such as negative thought reframing. This task relies on modifying cogn
TensorSharp supports DSpark on Deepseek v4 Flash 0731 now. Here is the benchmark result on 4x Nvidia A40 GPUs, cuda 12.8 with/without DSpark: Model: DeepSeek-V4-Flash-0731-UD-Q8_K_XL from https://hugg
Hugging Face CEO Clément Delague says “AI is actually an opportunity to fix a lot of the cybersecurity problems” because his company used Nvidia’s version of a Chinese open model to defend itself agai
The biggest issue with preview was its inability to follow rules prompts and skills. It seems like no matter what you do it ignores them. I've tried first person and second person. I've tried Chinese
In a world where building AI applications is getting easier every day, the biggest moat won’t be the application itself. It will be a deep understanding of your users. The winners will be the companie
arXiv:2607.28625v1 Announce Type: new Abstract: Embodied intelligence faces a fundamental data bottleneck. Models must capture how first-person perception, whole-body motion, dexterous manipulation, o