Knowledge catalogue
arXiv:2610.07654v1 Announce Type: cross Abstract: On-policy distillation (OPD) has attracted growing attention as an effective way to transfer capabilities from teacher models to student models. Recen
arXiv:2610.07014v1 Announce Type: new Abstract: RGB-D semantic segmentation has made notable progress by fusing RGB and Depth, yet mainstream models still learn features almost exclusively from pixel-
arXiv:2610.06973v1 Announce Type: new Abstract: Melt-pool monitoring is central to qualifying metal additive manufacturing (AM), yet no public event-camera benchmark exists for this domain. Event came
arXiv:2610.08626v1 Announce Type: cross Abstract: Diffusion models generate data through a continuum of denoising problems, and are widely observed to reveal coarse structure before fine detail. Yet,
arXiv:2610.08464v1 Announce Type: cross Abstract: Learned surgical simulators and world models can roll out plausible procedural futures, but they carry no grounded estimate of how often interventiona
arXiv:2610.04206v2 Announce Type: replace Abstract: Spatial intelligence is a fundamental skill in multiple domains, such as Science, Technology, Engineering, and Mathematics (STEM), Medicine, Archite
arXiv:2610.08063v1 Announce Type: cross Abstract: This paper presents the HINTT system submitted to the 2nd Challenge and Workshop on Multilingual Conversational Speech Language Model (MLC-SLM). We ad
Introducing River Recipes: our open-source initiative for turning promising research into vetted, reproducible training recipes. Our first recipe tackles text-to-SQL, where our trained open models bea
arXiv:2610.08405v1 Announce Type: cross Abstract: Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. E
arXiv:2610.07062v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these responses
arXiv:2610.07338v1 Announce Type: cross Abstract: Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies. To close this gap, we intro
I’m hitting rate limits on Together AI. For context, I’ve been working on an agentic repository indexing and benchmark generation tool, and I’m running multiple agents in parallel across models like L
arXiv:2610.08337v1 Announce Type: cross Abstract: Public redispatch records provide empirical data for grid congestion forecasting, but delayed reporting, zero-inflated distributions, and temporal shi
arXiv:2610.08327v1 Announce Type: new Abstract: Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by stati
arXiv:2610.08669v1 Announce Type: cross Abstract: On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient
Mistral AI introduced **Mistral Large 4** in October 2026 as a general‑purpose agentic model capable of gathering information and producing final deliverables across complex workflows. The launch high
arXiv:2610.08593v1 Announce Type: new Abstract: Traditional approaches for automated bug detection in video games, such as manual testing, can be beneficial for the improvement of quality assurance, b
arXiv:2610.07764v1 Announce Type: cross Abstract: Natural language processing (NLP) models can detect depression-related language in text written near the time symptoms are measured, but whether pretr
LIBERO is a robot manipulation benchmark: 130 tasks across five suites (spatial, object, goal, scene10, scene90), each with human demos and a language goal. It is the standard testbed for language-con
arXiv:2610.07842v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a language model to match a copy of itself conditioned on privileged context. Existing work varies what privil
arXiv:2610.06932v1 Announce Type: new Abstract: Cache-based test-time adaptation (TTA) for vision-language models is often hindered by background bias in global representations and unreliable entropy-
We spent the last weeks building a studio around YuE2, the open song model by m-a-p, and today it reaches its first release candidate. Write the style and the lyrics, and it composes, sings and render
arXiv:2606.16193v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representati
arXiv:2610.08403v1 Announce Type: new Abstract: Large Language Models (LLMs) require substantial computational resources, limiting their deployment on resource-constrained hardware. Ternary LLMs mitig
arXiv:2610.06994v1 Announce Type: cross Abstract: Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate
arXiv:2610.07529v1 Announce Type: new Abstract: Wave-based processors promise fast, energy-efficient Fourier layers for neural operators. They are usually validated on randomly sampled devices, but us
arXiv:2508.05880v3 Announce Type: replace-cross Abstract: Understanding human emotions is central to user-facing AI applications, safety alignment, and the simulation of human behavior. As emotional s
arXiv:2610.06974v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchma
arXiv:2610.08379v1 Announce Type: new Abstract: Visual counting is commonly formulated as counting a single specified target, with a model receiving an image-specific exemplar, text query, or target c
arXiv:2610.07261v1 Announce Type: new Abstract: A team of coding agents can look fine agent by agent yet fail as a team: each passes its own tests while the merged result is broken, and single-agent e
arXiv:2605.05780v2 Announce Type: replace Abstract: In the mid-twentieth century, mathematician and polymath John von Neumann created a computational system on an array of cells as a simple model of t
arXiv:2610.07115v1 Announce Type: cross Abstract: The order in which candidate responses are presented can change an LLM judge's verdict. Detecting such a position flip ordinarily requires judging eac
arXiv:2610.08760v1 Announce Type: cross Abstract: Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bri
You may ask why we’re doing this given that our main focus within LlamaParse (https://cloud.llamaindex.ai/) is building the best frontier models for document parsing and extraction. While we believe o
arXiv:2610.05774v1 Announce Type: new Abstract: Block drafters such as DSpark propose ranked candidates for several positions in one forward pass, and a tree verifier checks them in one pass of the ta
Hi ML Community, I am excited to share our latest framework, AFP-GIC, officially published in IEEE Access (2026). We have released the deployment codebase and hosted an interactive visual playground.
AI is driving the biggest infrastructure build-out in history, with @Google alone forecasting $200B of capex in 2026E. What are the real constraints on a system at this scale? Amin Vahdat is the chief
arXiv:2610.05367v1 Announce Type: cross Abstract: Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verificati
arXiv:2610.05274v1 Announce Type: new Abstract: Roadside traffic reasoning requires every free-form textual claim to be backed by visual evidence. Existing grounded multimodal large language models (M
ggml-openvino: skip unselected graph branches and support DUP Upstream #29622 adds a mixed token/embd branch to every input embedding graph through ggml_build_forward_select(). Its nodes are not flagg
ggml: refactor selective expert copying to user code (#29943) ggml: refactor selective expert copying to user code tests: enroll two models into selective expert copy test tests: use deepseek2 as test
arXiv:2610.04381v1 Announce Type: new Abstract: Fine-grained image editing requires more than producing a visually plausible result: an editor must execute the requested attribute change precisely whi
arXiv:2610.03822v1 Announce Type: new Abstract: Tokens have become a unified interface for multimodal foundation models, making visual-token communication a natural paradigm for efficient image delive
arXiv:2610.05921v1 Announce Type: cross Abstract: In generative models, Optimal Transport (OT) is used to improve Flow Matching (FM) by reducing noise-data coupling cost. However, different noise-to-o
arXiv:2610.03759v1 Announce Type: cross Abstract: Ocean wave forecasting is essential for maritime safety, offshore operations, and coastal resilience, yet remains challenging due to systematic biases
arXiv:2610.05400v1 Announce Type: cross Abstract: Long-video agents can actively gather question-relevant evidence, but they typically leave a central decision implicit: when has the agent seen enough
arXiv:2406.12150v2 Announce Type: replace Abstract: Post-hoc attribution is widely used to identify important model inputs, but evaluating whether these attributions identify truly informative feature
arXiv:2610.03911v1 Announce Type: new Abstract: Traditional sleep-staging methods apply the same model to every EEG epoch. Such uniform deployment expends computation on epochs that a smaller model co
arXiv:2610.05013v1 Announce Type: new Abstract: Lifelong physical agents must reason over extended interactions where past events continue to shape the world long after they disappear from view. Beyon
arXiv:2610.04517v1 Announce Type: cross Abstract: Deep time-series forecasting models have rapidly diversified, yet adapting them to a specific task still requires extensive expert effort in model sel
arXiv:2604.26654v1 Announce Type: cross Abstract: This paper presents an application of the biologically realistic JASTAP neural network model to classification tasks. The JASTAP neural network model
arXiv:2610.05353v1 Announce Type: cross Abstract: Fluorescence microscopy reveals where proteins localize, but only a limited number of proteins can be imaged in the same cell; generating these images
arXiv:2610.05812v1 Announce Type: new Abstract: Process control of advanced semiconductor nodes is not only pushing the limits of metrology equipment requirements in terms of resolution and throughput
arXiv:2610.05801v1 Announce Type: new Abstract: We propose a Gauss-map variation (GMV) model for image denoising that measures the spatial variation of the tangent-plane projectors of the scaled image
arXiv:2610.03861v1 Announce Type: cross Abstract: Foundation models and large-scale human data provide rich sources of manipulation intent, but translating this intent into multi-fingered robot behavi
arXiv:2610.04255v1 Announce Type: cross Abstract: Robotic manipulation often requires inferring task-relevant states from past interactions when the current observation alone is insufficient to determ
arXiv:2610.04969v1 Announce Type: new Abstract: Optimization in machine learning is usually expressed through iterative rules that update model parameters using information from the loss landscape. In
Here's a benchmark that uses Lilypond https://x.com/aug5thmusic/status/2096030719156089029 GPT-6 Astra has the best result yet on the Bach Benchmark. Its chorale contains no voice-leading errors, and
arXiv:2610.05809v1 Announce Type: new Abstract: Advanced semiconductor nodes are pushing the limits of feature sizes and require metrology with sub-nm resolution without compromising on the throughput
arXiv:2610.04507v1 Announce Type: new Abstract: Double descent has sparked considerable interest, with recent work relating it to the data, the model and the learning configuration. Practical fine-tun