Knowledge catalogue
arXiv:2609.04901v1 Announce Type: cross Abstract: Tabular foundation models (TabFMs) achieve strong performance on structured data, particularly for standard classification and regression problems. Ye
arXiv:2609.05152v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades
arXiv:2609.04555v1 Announce Type: new Abstract: Vision foundation models (VFMs) are valuable in data-scarce domains such as surgery, where a single pretrained backbone can provide rich representations
arXiv:2609.04778v1 Announce Type: new Abstract: Diffusion language models (DLMs) offer a non-autoregressive alternative for mobile edge agentic artificial intelligence (AI) by refining tokens through
arXiv:2609.05363v1 Announce Type: new Abstract: Trade-up recommendation identifies higher-quality alternatives that preserve a customer's purchase intent while offering upgraded benefits. Large langua
arXiv:2609.04782v1 Announce Type: new Abstract: Autoregressive (AR) large language models formulate reasoning as token-level probabilistic sampling, which induces three fundamental defects in complex
I got 2x 20GB RTX 3080s + 128GB of DDR4 2666hz RAM (only 4 of 6 channels populated) + a Xeon 6148 I've always been a llama.cpp person and I've been running Unsloth's Q4_K_XL quant of Qwen 3.8 Flash Ne
Our research team has been exploring an alternative approach to achieving interactivity and better responsiveness with LLM systems. One of the team members wrote up a post about it: https://research.y
arXiv:2609.04564v1 Announce Type: new Abstract: Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nev
Hi! Today I'm releasing MageTrail, a Danbooru/E621 proof of concept Full-Finetune of Microsoft's MageFlow 4B T2I model, using a diversity maximized condensed 41k images dataset (originally made by Lod
arXiv:2512.06813v3 Announce Type: replace-cross Abstract: High-performance concrete (HPC) requires complex mix design decisions involving interdependent variables and practical constraints. While data
arXiv:2609.05249v1 Announce Type: cross Abstract: As spaceborne computing systems increasingly rely on neural network (NN) accelerators, the opacity of commercial, black-box architectures severely res
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
arXiv:2609.04561v1 Announce Type: new Abstract: Whisper is a widely used foundation model for automatic speech recognition (ASR), but its generative decoder can produce fluent hallucinated transcripts
arXiv:2609.04344v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to interpret language model activations, but SAE training and latent labelling are typically repeated for e
arXiv:2609.04545v1 Announce Type: cross Abstract: Robots interacting with people must recognize not only explicit commands, but also social cues such as invitations, refusals, and unavailability. In r
arXiv:2606.17398v2 Announce Type: replace-cross Abstract: Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it
arXiv:2609.04705v1 Announce Type: cross Abstract: Passive cooling eliminates the energy overhead and mechanical failure modes of fans, making it attractive for edge deployment, yet sustained Deep Neur
arXiv:2603.08234v2 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety
arXiv:2502.00285v3 Announce Type: replace-cross Abstract: Trajectory similarity is fundamental to many spatio-temporal data mining applications. Recent studies propose deep learning models to approxim
I recently ported VDN-H3 (Video DeltaNet for MiniMax H3) to Vpipe and tested it on an M5 Pro 24GB. The benefit scales with both sequence length and resolution: at 832×480, VDN-H3 starts to pull ahead
I've been tinkering with local LLMs since the beginning of the year when I had an Intel Arc B580 and 32 GB of DDR5. Curiosity got the best of me and I bought the first R9700 about half a year ago, als
Jensen has the best gig on the planet. But it is impossible to see how all this is sustainable. Consider the following: Each new model costs vastly more to develop. That’s fabulous for him! On the oth
https://huggingface.co/XHToken/Spark-X2.5-4B-GGUF https://huggingface.co/XHToken/Spark-X2.5-1.7B-GGUF from XHToken: We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose l
Time for another update! We have been busy and managed to improve the gains substantially (mostly from exploring existing llama cpp PRs and adopting relevant things). Among other things the README.md
arXiv:2609.03139v1 Announce Type: new Abstract: Deep neural networks (DNNs) are increasingly deployed in real-world vision systems, yet their predictions can be covertly manipulated by backdoor attack
arXiv:2609.04198v1 Announce Type: new Abstract: Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rare
arXiv:2609.03707v1 Announce Type: new Abstract: We present our submission to the IJCAI 2025 'Counterfactual Routing Competition' (CRC 25). The goal of the competition is to find counterfactual explana
arXiv:2609.03894v1 Announce Type: new Abstract: Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants.
arXiv:2609.03438v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are increasingly used to execute natural-language instructions on user interfaces, yet real users may issue infeas
arXiv:2609.03662v1 Announce Type: new Abstract: Recent unlearning methods (e.g. NPO, DPO, LUNAR) make use of refusal alignment to suppress forgotten data. However, it has been shown that refusal respo
arXiv:2609.03705v1 Announce Type: new Abstract: In this paper we study linear non-Gaussian acyclic models (LiNGAM) when used in federated environments. These causal models allow one to go beyond Marko
NVIDIA Jetson can run compact open‑source reasoning models such as Nemotron 3.5 Lightning (a mixture‑of‑experts architecture with 30 B total parameters but only ~3 B active per token) and dense Qwen 3
arXiv:2609.03193v1 Announce Type: cross Abstract: Nested sampling (NS) resolves the thermodynamics of an atomistic system from a single simulation, but its practical reach is limited by the Markov-cha
arXiv:2405.21047v4 Announce Type: replace Abstract: Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-forme
arXiv:2609.03329v1 Announce Type: cross Abstract: Long-duration gravitational-wave modelling must resolve fast orbital motion together with slow dissipative evolution while preventing small numerical
arXiv:2508.00669v2 Announce Type: replace-cross Abstract: The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability
arXiv:2609.02988v1 Announce Type: new Abstract: High-fidelity TCAD simulation of drift-diffusion transport remains the workhorse of emerging FinFET device design, but it is computationally expensive,
Moving Large Language Models (LLMs) from experimental prototypes into enterprise production exposes a critical truth: your infrastructure dictates both your performance ceilings and your unit economic
Nvidia Corp. is targeting artificial intelligence agent enthusiasts with a new local distributed clustering tool called the Personal AI Router. It enables them to use any idle Mac computers or PCs lyi
arXiv:2609.03420v1 Announce Type: cross Abstract: Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data, yet its deploy
arXiv:2609.03937v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) complements parametric models with retrieved external evidence. The same idea is attractive for continuous-output
arXiv:2609.03142v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies fuse multimodal sensory inputs, but training on limited and homogeneous robot demonstrations encourages spurious
arXiv:2609.03376v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has made dense retrieval over large document collections a standard building block. Organizations increasingly ou
arXiv:2609.03697v1 Announce Type: cross Abstract: In the natural sciences, symmetries and cause-effect relationships are ubiquitous. Yet for complex machine-learning tasks, like world-modeling in rein
arXiv:2609.03702v1 Announce Type: new Abstract: General-purpose code embeddings power tools for code search, classification, and retrieval. Compact transformer encoders for code typically rely on eith
arXiv:2609.02987v1 Announce Type: new Abstract: Reinforcement learning typically optimizes average reward. For generative policies, the average can hide an important distinction: two policies can achi
arXiv:2609.03585v1 Announce Type: new Abstract: Thermal infrared imaging offers reliable perception in darkness and adverse weather, but thermal datasets remain scarce, motivating extensive work on tr
arXiv:2609.04202v1 Announce Type: new Abstract: While data-driven 3D shape correspondence estimation has recently seen substantial progress, robust matching under partial observations and strong non-i
Tulip uses two techniques to lower latency and boost throughput. CUDA graphs pre‑record GPU work so it launches in one call, reducing CPU overhead. LazyTensors tracks results asynchronously, letting t
arXiv:2609.03378v1 Announce Type: new Abstract: Depth can resolve appearance ambiguity in RGB-D salient object detection (SOD), yet sensor depth is not uniformly reliable. Missing regions, blurred bou
arXiv:2609.01902v1 Announce Type: cross Abstract: Assessments of cultural alignment have become an important part of the development and improvement of large language models (LLMs). However, the major
arXiv:2410.15184v2 Announce Type: replace-cross Abstract: As trajectories sampled by policies used by reinforcement learning (RL) and generative flow networks (GFlowNets) grow longer, credit assignmen
arXiv:2609.02215v1 Announce Type: new Abstract: Safety alignment trains large language models to refuse harmful requests stated plainly, but that training is applied mostly to surface form. Requests t
Banger paper from Google DeepMind and colleagues. (bookmark it) A model reads its entire KV cache on every generated token, even though it ends up attending to a tiny slice of it. In other words, if y
arXiv:2609.01833v1 Announce Type: new Abstract: Sentence-level recognition of depression symptoms is challenging because similar expressions can differ in symptom relevance, and language-model inferen
arXiv:2607.10110v2 Announce Type: replace Abstract: Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional ind
arXiv:2609.02074v1 Announce Type: new Abstract: Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based
arXiv:2609.01992v1 Announce Type: new Abstract: Agent evaluations face two distinct evidentiary questions: whether a reported claim is recomputable from retained evidence (sufficiency), and whether th
arXiv:2609.02264v1 Announce Type: new Abstract: Adapting the communication topology of an LLM multi-agent system to each query improves both accuracy and efficiency, yet current designers treat this a