Knowledge catalogue
arXiv:2609.12495v1 Announce Type: cross Abstract: Large language models are being organized into multi-agent systems with specialized roles, but whether such specialization produces distinct forecasts
arXiv:2609.12655v1 Announce Type: new Abstract: Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, ex
arXiv:2609.12367v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) are the standard tool for auditing the privacy risks of machine learning models. Given a query point, an MIA aims
arXiv:2609.12409v1 Announce Type: new Abstract: High-frequency surgical maneuvers in ophthalmology necessitate high-fidelity temporal modeling, yet characterizing long-range procedural dependencies re
arXiv:2609.12899v1 Announce Type: new Abstract: Full waveform inversion (FWI) estimates subsurface velocity from seismic recordings, but its ill-posedness and nonlinearity make accurate reconstruction
arXiv:2609.12223v1 Announce Type: new Abstract: Collision cross section (CCS), derived from ion mobility mass spectrometry, is a common descriptor for molecular annotation. Prediction is challenging f
Pushed out this new update, hopefully decreases the instances of crashes. I torture tested this one for ~12 hours after my fixes and found no instability. Q4 K XL needs more fine tuning, which I will
VLLM Benchmark: Prefill, Prompt processing - avg, 871.93 tok/s (3 hours constant running xhigh) - 10K prompt, 1000.26 tok/s (16 runs) - 90K prompt, 743,59 tok/s (16 runs) Decode, tok gen - avg, 38.39
> 'make an svg of a frog playing on a chello on the back of a whale with carribean island in the back.' interestingly the svg looks different in the OpenWebUi preview then when looked at in preview (o
I'm documenting a reproducible setup for running current llama.cpp on a mixed AMD Vega system with both: Radeon RX Vega 64 / Vega10 / gfx900 (8GB HBM2) Radeon Instinct MI50 (Vega20) / gfx906 (16GB HBM
What I have: - CPU: EPYC 7551 (32c/64T, Zen 1) - Board: Supermicro H11SSL-i (SP3), Rev 2.0 - RAM: 128 GB DDR4-2133 (all 8 channels full) - GPU: 2x RTX 3090 (48 GB total, PCIe 3.0) - 1500 W PSU What I
arXiv:2609.11660v1 Announce Type: new Abstract: In recent years, artificial intelligence has made extraordinary progress thanks to large-scale models capable of generalization and the generation of co
Hey everyone — I’m building TensorSharp, an open-source LLM inference engine. Here are the latest DeepSeek V4.1 Flash GGUF results using its native ggml_cuda backend. Setup: 8× NVIDIA A40, layer split
First off, I know that GLM, Qwen, and DeepSeek absolutely dominate in terms of SOTA Open Source models, and that’s what I use in my personal projects and for school, however, I’m also responsible for
arXiv:2609.11636v1 Announce Type: new Abstract: Domain practitioners understand their business constraints but may lack operations-research expertise or dedicated support. LLM-based optimization agent
arXiv:2609.11294v1 Announce Type: new Abstract: High-fanout agent workloads create a growing memory bottleneck because a single task may spawn many concurrent sandbox sessions. Yet these sandboxes are
arXiv:2609.11152v1 Announce Type: cross Abstract: The open web ran on an unwritten bargain: sites admitted crawlers, and search engines sent visitors back. Public measurements show that bargain breaki
arXiv:2408.02920v2 Announce Type: replace-cross Abstract: The rapid advancement of AI technology has led to widespread applications of agent systems across various domains. However, the need for detai
arXiv:2609.09374v1 Announce Type: new Abstract: Arctic maritime navigation is becoming increasingly important as changing sea-ice conditions expand seasonal accessibility while simultaneously introduc
Hi! I've been following this community for quite a while and have difficulty figuring out what to put on my 3080 12gb - I know Qwen 3.6 35B 3A was the go-to choice when it first came out, but I'm curi
arXiv:2609.11870v1 Announce Type: new Abstract: A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Au
arXiv:2602.19326v3 Announce Type: replace-cross Abstract: Urban renewal requires incremental modifications to existing geospatial plans, yet manually updating complex layouts under spatial constraints
arXiv:2609.11878v1 Announce Type: new Abstract: Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detectio
arXiv:2609.10706v1 Announce Type: cross Abstract: Human video datasets have emerged as a compelling alternative to expensive real-robot data, offering rich diversity at scale. To bridge the human-to-r
arXiv:2603.15617v2 Announce Type: replace Abstract: Can AI make progress on important, unsolved mathematical problems? Large language models are now capable of sophisticated mathematical and scientifi
arXiv:2609.11892v1 Announce Type: new Abstract: As Speech Large Language Models (speech-LLMs) become increasingly multilingual, Arabic remains significantly underrepresented, highlighting the need for
arXiv:2603.20278v2 Announce Type: replace-cross Abstract: Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. Howev
arXiv:2502.17017v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi
arXiv:2609.11360v1 Announce Type: new Abstract: Automated inspection of segmental tunnel linings requires adaptive segmentation from 3D point clouds, yet expert-tuned pipelines often degrade when tunn
arXiv:2609.09409v1 Announce Type: cross Abstract: Near-field localization is a promising technique for high-resolution multi-user positioning in future wireless systems, but its performance is often d
arXiv:2609.10825v1 Announce Type: cross Abstract: Detecting brain metastases in magnetic resonance imaging (MRI) remains challenging because lesions vary widely in size and appearance, with very small
arXiv:2609.10914v1 Announce Type: cross Abstract: Label-free virtual staining offers a compelling, non-destructive alternative to standard histopathology; however, its clinical adoption is hindered by
arXiv:2609.11650v1 Announce Type: new Abstract: Accurate identification of end-diastole (ED) and end-systole (ES) in echocardiography underpins the quantification of ventricular function, yet manual s
arXiv:2609.10923v1 Announce Type: new Abstract: Graph captions should help readers understand graph structure, rather than simply translate adjacency matrices into long textual edge lists. A useful gr
arXiv:2609.11063v1 Announce Type: cross Abstract: Large language models learn similar behaviours, yet it remains unclear what structure they share or how to change one behaviour without disturbing oth
i've been thinking about this more after trying different agent setups. the model isn't the only thing that determines how well an agent performs. The harness around the model matters a lot too. With
arXiv:2609.11156v1 Announce Type: new Abstract: All-in-One medical image restoration (MedIR) aims to address diverse tasks across modalities and degradation types using a single universal model. Exist
arXiv:2609.11875v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models have improved robotic manipulation, yet observation-to-action learning remains limited by a funda
LM Studio is a US‑hosted platform that enables “Zero Data Retention” by default, meaning user inputs are not stored after processing. It currently hosts the DeepSeek V4.1 Flash model—a 552 B multimoda
arXiv:2609.11390v1 Announce Type: cross Abstract: State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial
arXiv:2609.10263v1 Announce Type: new Abstract: Persistent language agents need stored experience to remain available across time, while each answer requires evidence suited to a particular question.
arXiv:2609.11772v1 Announce Type: cross Abstract: Cross-cultural understanding has become increasingly important in today's highly connected, cross-national world. The success of LLM-based technologie
arXiv:2609.07075v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is commonly evaluated by whether the final answer is correct. That test is insufficient: an answer can match its re
arXiv:2609.08592v1 Announce Type: new Abstract: Evaluating tool-augmented LLM agents requires diverse, realistic user inputs yet most evaluation frameworks use flat role descriptions ('you are an angr
arXiv:2510.11454v2 Announce Type: replace-cross Abstract: Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solely
arXiv:2609.09356v1 Announce Type: new Abstract: At Noora Health, our nurses answer more than 50,000 medical queries per month on our WhatsApp-based service that provides caregivers with on-demand supp
arXiv:2609.05446v1 Announce Type: new Abstract: We introduce AutoFyn, an agent harness inspired by the Expert Iteration algorithm, adapting a frozen model across many rounds by updating persistent sta
arXiv:2609.10518v1 Announce Type: new Abstract: fMRI foundation models increasingly aggregate heterogeneous data across brain states, cohorts, and acquisition settings, yet pretraining domains are com
arXiv:2609.09766v1 Announce Type: new Abstract: Churn models typically identify high-risk customers but do not specify which feasible retention action should be considered or why that action is approp
The downside of uncensoring a model is that it is known to potentially damage it, but CyberTiel is an even more capable software engineer than its censored TielCoder base, while allowing offensive sec
arXiv:2609.06674v1 Announce Type: cross Abstract: We present a new attack that reconstructs the text generated by locally hosted LLMs by observing CPU cache activity during detokenization. Unlike prio
arXiv:2609.10253v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in globally used assistants, yet their default choices in culturally grounded everyday situations
arXiv:2609.09586v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are increasingly pre-trained on synthetically generated time series trajectories, where the data generating proc
arXiv:2609.07194v1 Announce Type: new Abstract: We present EmoMed - a multimodal medical consultation agent that adapts its responses based on users' emotional states while maintaining clinical accura
arXiv:2504.18376v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, a
arXiv:2609.06731v1 Announce Type: cross Abstract: Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event, and therefore relies on accuratel
arXiv:2609.05806v1 Announce Type: new Abstract: Emotion Recognition in Conversations (ERC) aims to identify speakers' emotions in multi-turn dialogue. Accurate emotion recognition can support a wide r
arXiv:2609.07153v1 Announce Type: cross Abstract: Minimal-pair benchmarks such as BLiMP evaluate linguistic knowledge by testing whether language models (LMs) prefer acceptable sentences over minimall
arXiv:2609.08899v2 Announce Type: replace-cross Abstract: Speech deepfakes can mimic a speaker's voice convincingly enough to deceive listeners and automated systems. This has driven strong progress i
arXiv:2609.08599v1 Announce Type: new Abstract: Large Language Model (LLM) agents are evolving from single-session tools toward long-term personal assistants that must adapt to individual users across