Knowledge catalogue
arXiv:2609.04859v1 Announce Type: new Abstract: As vision-language models (VLMs) rapidly advance in image understanding, cross-modal reasoning, and complex instruction execution, instruction-following
arXiv:2609.04842v1 Announce Type: cross Abstract: Time-series data in clinical settings is crucial for capturing dynamic changes in a patient's health over time, enabling timely diagnosis, personalize
arXiv:2609.05381v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on molecular property benchmarks, but accuracy cannot distinguish a model that predicts a proper
arXiv:2609.04274v1 Announce Type: cross Abstract: Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family
arXiv:2609.05395v1 Announce Type: new Abstract: Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-premise LLM agents that chain multiple tool-calls across
arXiv:2609.05070v1 Announce Type: new Abstract: Automated gastrointestinal (GI) endoscopy classification requires models that generalize across diverse modalities and class distributions, often far fr
arXiv:2603.18892v2 Announce Type: replace-cross Abstract: Spatial reasoning is foundational for Vision-Language Models (VLMs), particularly when deployed as Vision-Language-Action (VLA) agents in phys
DISCLAIMER I ramble a lot and am not good at focusing on documentation and or coherent thoughts. TLDR I did things I made a thing and it works for me. I will try to answer any questions. A few people
TL;DR My TAK quant of Qwen 3.8 27b scored 82.81% on reasoning, comparted with 77.34% for the byte matched Unsloth UD IQ2_S and 83.59% for BF16. Edit: Some of you have tried coding with this reasoning-
arXiv:2609.04602v1 Announce Type: new Abstract: Fixed 3D Gaussian Splatting (3DGS) reconstructions provide realistic novel views but lack the traversability constraints, valid goals, and closed-loop p
arXiv:2609.05385v1 Announce Type: new Abstract: LLM decision components that can operate within agent workflows often produce action-relevant recommendations or judgements together with explanations.
How it works. The model being tested is given a server capable of running it's weights and full context. That server is placed in a median priced apartment. The AI is given a bank account with for ren
arXiv:2609.05139v1 Announce Type: new Abstract: Long-form literary narratives pose a distinctive information-processing challenge for retrieval-augmented generation: relevant evidence is distributed a
arXiv:2609.04921v1 Announce Type: cross Abstract: Diffusion probabilistic models can capture the multi-modal, interaction-rich distribution of joint future trajectories in driving scenes. We show that
arXiv:2609.05260v1 Announce Type: new Abstract: Natural-language instruction changes can directly alter robot behavior. A reliable embodied system should preserve its action when the task is unchanged
arXiv:2609.05318v1 Announce Type: new Abstract: Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures
I've built and open-sourced ParaRNN, a PyTorch/Triton library that parallelizes the training of non-linear recurrent architectures across time using Newton-Raphson iterations mapped to associative pre
arXiv:2609.04476v1 Announce Type: new Abstract: Performance modeling is central to hardware design and software optimization, yet constructing these models requires structured reasoning about computat
arXiv:2609.04598v1 Announce Type: cross Abstract: We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary knowledge and clinical reasoning in large language
arXiv:2609.05194v1 Announce Type: cross Abstract: The number of discrete class-separability jumps observed during ResNet finetuning is examined empirically as a predictor of final test accuracy. Acros
arXiv:2609.04943v1 Announce Type: new Abstract: Recent benchmarks such as PowerGraph provide large collections of power-grid graphs for cascading-failure classification. Graph neural networks (GNNs) a
arXiv:2609.04715v1 Announce Type: new Abstract: Personalizing large language models (LLMs) is essential for delivering AI assistance that aligns with individual users' styles, intents, and preferences
arXiv:2603.05623v2 Announce Type: replace-cross Abstract: Camera-LiDAR fusion is widely used in autonomous driving to enable accurate 3D object detection. However, bird's-eye view (BEV) fusion detecto
arXiv:2609.05235v1 Announce Type: cross Abstract: Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language
arXiv:2609.04867v1 Announce Type: cross Abstract: Text-to-audio-video (T2AV) generation has advanced rapidly, but its evaluation still underestimates the audio modality. Existing benchmarks either tre
arXiv:2609.04793v1 Announce Type: new Abstract: Proteins perform diverse cellular functions, and even single amino-acid substitutions can alter stability, activity, or molecular interactions. Protein
arXiv:2609.05038v1 Announce Type: new Abstract: Species identification in camera trap images has been widely studied, but key ecological modeling tasks such as species abundance or density estimation
arXiv:2609.04263v1 Announce Type: cross Abstract: Low-bit key--value (KV) caches reduce the memory required for autoregressive decoding, but the resulting quality loss depends on the model and quantiz
arXiv:2609.04271v1 Announce Type: new Abstract: Wi-Fi-based human activity recognition (HAR) has become an important part of integrated sensing and communications, paving the way for a range of contex
I just tried to run Qwen 3.8 27B 4bit qwant on 5060ti 16GB and got terrible results. With Qwen 3.6 I got something around 15-20 tok/s. Are there any combination of parameters or tweeks how to push the
Long time user of 3.6 27b, switched over to Next Flash since it's a logical step up even from 3.8 27b. It's soooo verbose, i'm talking 13 minutes of thinking time on single turn coding requests at app
Since the Qwen3.5 0.8B model is an interesting one for small specialized fine tunes, I was curious how fast it can run on CPUs. Why CPUs? Mainly because I want to use it as a local dictation cleanup m
I’ve been setting up an M1 Max Mac Studio (24-core GPU, 32GB unified memory) as a local LLM server and wanted to compare MLX vs llama.cpp on Qwen3.8-27B. I tried to keep the model footprint and benchm
My XFX Radeon RX 7900 GRE 16GB Vram GPU struggles with models over 20B size. I added my Radeon RX 480 8GB Vram GPU to the system and ran a few benchmarks using llama.cpp Ubuntu Vulkan build 10453. htt
arXiv:2609.05202v1 Announce Type: cross Abstract: Multi-modal learning has demonstrated strong potential in medical applications by integrating heterogeneous data sources such as medical imaging, clin
Really strong benchmark paper on coding agents. Claude Opus 5 running under Claude Code passes 23.9% of the evaluations. An expert human reference scores 82.2%. Here is what the task actually is. The
arXiv:2609.04878v1 Announce Type: cross Abstract: Fraudulent messages sent via Short Message Service (SMS) are increasingly obfuscated to evade cost-conscious classifiers in production systems. In Chi
arXiv:2609.04808v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavior, but it remains unclear whether a feature found i
arXiv:2609.05403v1 Announce Type: cross Abstract: Retail search systems serve diverse geographic regions with distinct query patterns, vocabularies, and product preferences, creating significant data
arXiv:2609.04823v1 Announce Type: cross Abstract: Although automatic text simplification (ATS) is critical for accessibility, its progress has not matched the rapid evolution of broader natural langua
arXiv:2609.04533v1 Announce Type: cross Abstract: Prompt injection is widely recognized as a major security threat to AI agents that interact with untrusted external data, such as websites, documents,
arXiv:2603.24131v2 Announce Type: replace-cross Abstract: Message passing is a core mechanism in Graph Neural Networks (GNNs), enabling the iterative update of node embeddings by aggregating informati
arXiv:2609.04763v1 Announce Type: new Abstract: Due to resource constraints or external and internal uncertainties, clients in real-world federated learning systems are often intermittently available
arXiv:2609.04689v1 Announce Type: cross Abstract: Early identification of Alzheimer's disease (AD) remains challenging because established assessment methods can be costly, resource-intensive, or unsu
arXiv:2609.05295v1 Announce Type: new Abstract: On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher qu
arXiv:2609.05199v1 Announce Type: cross Abstract: We consider safety-critical control problems involving multiple requirements with different priorities and uncertainty in their evaluation. We represe
arXiv:2609.05324v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchma
arXiv:2609.05401v1 Announce Type: cross Abstract: Vision-language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajecto
arXiv:2609.04634v1 Announce Type: cross Abstract: As generative audio models grow in complexity, the computational and ecological costs of synthesizing everyday sounds have become increasingly prohibi
arXiv:2609.05141v1 Announce Type: new Abstract: Scientific papers require models to reason jointly over text, equations, figures, tables, code, and datasets while preserving the provenance of supporti
arXiv:2609.04439v1 Announce Type: new Abstract: Automated aortic segmentation in 4D flow MRI is essential for reproducible hemodynamic assessment but is limited by scarce dense annotations and high co
arXiv:2601.18049v2 Announce Type: replace Abstract: Significant progress has been made in semi-supervised hyperspectral image (HSI) classification regarding feature extraction and classification perfo
arXiv:2609.04629v1 Announce Type: new Abstract: A runtime gate for an LLM tool agent is usually cast as a filter. In a ReAct loop a rejected proposal is followed by another at the same state, so the g
arXiv:2609.05125v1 Announce Type: new Abstract: Evaluating the calibration of Large Language Models (LLMs) is critical for their safe deployment as zero-shot classifiers. Yet, commercial API providers
arXiv:2407.18897v2 Announce Type: replace Abstract: Molecular optimization, the process of designing molecules with desirable properties, represents a critical challenge in drug discovery. Recent adva
arXiv:2609.05012v1 Announce Type: new Abstract: Federated scientific machine learning enables institutions to train neural surrogates without centralizing local physical data, yet studies of partial d
arXiv:2609.05232v1 Announce Type: new Abstract: Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runtime, compute, and operational constraints determine w
arXiv:2601.04202v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly applied to telecom engineering tasks, yet perform poorly on 3GPP specifications. These standards
arXiv:2609.05282v1 Announce Type: new Abstract: Reliable robot-to-human handover requires the robot to infer when the person is ready to receive the object, and release it safely, comfortably, and at
https://preview.redd.it/3p6234jzk2oh1.png?width=900&format=png&auto=webp&s=b9eab3351d6c6dbd4d5b3fd677a6c40b57f18167 https://huggingface.co/tencent/EVIE-8B 🌟 Highlights SOTA Retrieval Performance: 66.7