Maglev: Sliding Recurrent Memory
arXiv:2608.02870v1 Announce Type: new Abstract: We introduce ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizabl
Knowledge catalogue
arXiv:2608.02870v1 Announce Type: new Abstract: We introduce ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizabl
arXiv:2608.02964v1 Announce Type: new Abstract: Quantitative longwave thermography of heritage surfaces is limited by the global-constant emissivity assumption in inverse-Planck temperature retrieval;
arXiv:2608.02642v1 Announce Type: cross Abstract: Accelerating scientific discovery is among the most consequential applications of AI, and computational biomolecular simulation stands out as a partic
arXiv:2608.00794v2 Announce Type: replace Abstract: Agentic AI evaluation pipelines produce benchmark scores that justify deployment decisions, safety certifications, and regulatory compliance claims.
arXiv:2608.02613v1 Announce Type: cross Abstract: Edge-deployed personal memory assistants must handle private interpersonal conversations on-device with open-weight models. Yet, existing memory bench
arXiv:2511.03942v2 Announce Type: replace-cross Abstract: We present MIDI-LLM, a recipe that improves multitrack text-to-MIDI generation via adapting Large Language Models (LLMs). MIDI-LLM expands an
arXiv:2608.03525v1 Announce Type: new Abstract: In organic chemistry papers and patents, molecular structures, reaction schemes, and experimental conditions are often presented as molecular structure
arXiv:2608.03142v1 Announce Type: cross Abstract: We study contextual dynamic pricing with arbitrary covariate sequences and bounded, possibly nonbinary purchase quantities. Demand follows a semiparam
French artificial intelligence startup Mistral AI SAS today introduced a lightweight multimodal safety artificial intelligence open-weight model that can classify outputs for AI models that outperform
arXiv:2608.03397v1 Announce Type: new Abstract: MMLongBench-Doc is a long-document QA benchmark of 1,082 questions over 135 PDFs. Two properties of it push measured scores away from the quantity they
arXiv:2203.17257v2 Announce Type: replace Abstract: Salient Object Ranking (SOR) aims to estimate the relative saliency order among multiple salient objects. While SOR has been extensively studied in
TensorSharp's MoE CPU-offload feature has been merged into main. Here is the parameters description of this feature: Mixture-of-Experts CPU offload: --n-cpu-moe <N> | -ncmoe <N> Keep the routed MoE ex
arXiv:2608.03275v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of large language models, but existing MoE-based PEFT methods typically improve capa
arXiv:2608.03664v1 Announce Type: new Abstract: Accurate diagnosis in Digital Pathology (DP) relies on high-resolution whole-slide images, yet clinical deployment is often limited by hardware costs. S
arXiv:2608.03474v1 Announce Type: new Abstract: Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks pre
arXiv:2608.03708v1 Announce Type: new Abstract: Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single
arXiv:2608.03882v1 Announce Type: cross Abstract: Geospatial reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to navigation and logis
arXiv:2608.03885v1 Announce Type: new Abstract: Vision-language models exhibit remarkable zero-shot capabilities but suffer significant performance degradation under distribution shifts. While test-ti
arXiv:2604.01973v2 Announce Type: replace Abstract: When evaluating identity-focused tasks such as personalized generation and image editing, existing vision encoders entangle object identity with bac
arXiv:2608.02778v1 Announce Type: new Abstract: We present a novel application of Neural Networks with Local Converging Inputs (NNLCI) to improve the efficiency of existing numerical methods for prici
arXiv:2608.02845v1 Announce Type: new Abstract: Tabular model performance degrades when feature distributions change over time or the relationship between features and outcome variables change over ti
arXiv:2608.03839v1 Announce Type: new Abstract: Training-free speculative decoding drafts by matching an exact suffix of the context against a pool of earlier context. That lookup misses correct draft
arXiv:2608.03428v1 Announce Type: cross Abstract: Image based dietary assessment offers a scalable alternative to self reported food diaries, yet fine-grained food recognition remains challenging due
arXiv:2608.03887v1 Announce Type: new Abstract: Fine-tuning a large language model on new data degrades what it previously learned. We present Omega-S, a drop-in penalty computed from the weight matri
arXiv:2608.03197v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) improves generalization by seeking parameters whose loss is robust to local adversarial perturbations, but the quanti
arXiv:2608.02996v1 Announce Type: new Abstract: Latin America is missing a foundational layer for native AI development: the benchmark layer. The benchmark layer does two things no other layer can - i
arXiv:2608.02949v1 Announce Type: new Abstract: Latin America is missing two foundational layers of AI infrastructure: the dataset layer and the benchmark layer. This paper targets the dataset layer.
arXiv:2608.02615v1 Announce Type: cross Abstract: Cancer diagnosis and characterization require integrating complementary evidence from radiology, pathology, genomics, and clinical metadata. However,
arXiv:2608.03249v1 Announce Type: new Abstract: Cold-Start Active Learning (CSAL) aims to select a valuable subset from an unlabeled pool without any prior knowledge or human assistance. Existing meth
arXiv:2507.07754v3 Announce Type: replace-cross Abstract: Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show
Back in 2024 I tweeted screenshots of a game concept generated by GPT-3 and some concept 'art' created using DALL-E. Today, on the fourth anniversary of that tweet, I decided to see if Claude Fable 5
arXiv:2608.03878v1 Announce Type: new Abstract: Synthetic power-grid scenarios are essential for planning, resilience assessment, contingency analysis, and data-driven power-system applications. Recen
arXiv:2608.03034v1 Announce Type: cross Abstract: Reasoning-enhanced large language models have achieved remarkable improvements in planning tasks, yet their deployment in embodied systems remains imp
arXiv:2608.02844v1 Announce Type: cross Abstract: We develop a class of diffusion-based stochastic particle optimisation methods for loss functions with intractable gradients. Specifically, we conside
arXiv:2608.04010v1 Announce Type: cross Abstract: Existing scaling strategies for Multimodal Large Language Models (MLLMs) typically expand either model parameters or sequential inference computation,
arXiv:2608.04003v1 Announce Type: new Abstract: Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI agents offer a concrete setting for s
arXiv:2608.03691v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway
arXiv:2608.03048v1 Announce Type: cross Abstract: Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: se
arXiv:2608.03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters. Though powerful, this introduces a
arXiv:2603.24413v2 Announce Type: replace Abstract: Poetry generation in Sanskrit typically requires the verse to be semantically coherent and adhere to strict prosodic rules. In Sanskrit prosody, eve
arXiv:2608.03041v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) approaches for flexible job shop scheduling (FJSP) heavily rely on attention-centric architectures to achieve state-
arXiv:2608.03612v1 Announce Type: cross Abstract: Virtual contrast enhancement (VCE) synthesizes enhanced breast MR images from pre-contrast acquisitions. Modern latent generators offer strong image p
Prime Agent is an open-source coding and research agent for general and long-running work. A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficien
arXiv:2512.01370v2 Announce Type: replace-cross Abstract: Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routin
arXiv:2608.03294v1 Announce Type: new Abstract: We study the problem of learning multi-head softmax attention from black-box input-output access. The learner may query arbitrary real-valued token sequ
So one of yall mentioned that cuda 13.1 or 13.2 is broken for unsloth so I looked in to it, and they were right. I had 13.2 installed, after I switched to 13.3 no more looping!!! Before the cuda updat
arXiv:2603.09986v3 Announce Type: replace-cross Abstract: Hallucinations, the tendency for large language models to provide responses with factually incorrect and unsupported claims, is a serious prob
arXiv:2608.03854v1 Announce Type: new Abstract: When decoder language models are used as classifiers, predicted class probabilities depend on implementation choices, including the prompt template, ver
arXiv:2608.02980v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to f
Questions & Responses(in BOLD) below. Favorite question(s) moved to end of the thread with combined responses(removed duplicates). Be optimistic folks. I'm sure we're getting other models too apart fr
Qwen-Image-3.0-Pro is live on Qwen Cloud now! Try it out👇 https://www.qwencloud.com/models/qwen-image-3.0-pro?utm_content=g_20000001188 🔔 Qwen-Image-3.0 is now live on Qwen Cloud! Ranked #1 among Chin
People may remember the Qwen3-TTS llama.cpp demo from a few months ago. That PR said it probably wouldn’t be merged because llama.cpp was missing some of the graph and API pieces it needed. A new impl
Qwen3.8-Max hits #2 in Image-to-WebDev Arena! It sees, it builds~😎 Exciting news: Qwen3.8-Max by @Alibaba_Qwen is #2 in Image-to-WebDev Arena! With 1,631 pts, it’s trailing only Claude Opus 5 (Max) by
arXiv:2608.03219v1 Announce Type: new Abstract: Benchmark gains are often treated as evidence of greater LLM capability. Yet the same gain can reflect different changes in model behavior. A model may
arXiv:2608.03135v1 Announce Type: cross Abstract: Text-to-image diffusion models can generate individual concepts well, but they often omit or merge concepts incorrectly with multiple concepts. We tra
arXiv:2608.02636v1 Announce Type: cross Abstract: Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying mode
arXiv:2608.03512v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance on text-to-knowledge graph generation and related tasks. Nevertheless, it is still unclear
arXiv:2608.03745v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring. However, monitoring relies on faithfulness, i.e., the model output str
arXiv:2608.03341v1 Announce Type: cross Abstract: Large language models (LLMs) have substantially improved code generation, yet achieving strong functional correctness remains difficult, especially fo
arXiv:2608.02948v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD), where a single model acts as both student and teacher with different contexts, has shown promise in verifiable dom