Knowledge catalogue
arXiv:2609.06974v1 Announce Type: cross Abstract: Large language models achieve strong performance across diverse tasks, but deployment remains costly because of memory, latency, and energy demands. S
Two big updates 1. I published an @FT op-ed on the OpenAI/HF incident & follow-ups 2. We’re starting an Open Alignment team at @huggingface to work on safety & alignment for open models, incl cybersec
arXiv:2609.09396v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) advance toward physical deployment, the focus has remained on action-oriented Embodied AI evaluated on subject-centric
arXiv:2609.09887v1 Announce Type: new Abstract: LLMs have been used to simulate human decision-making in professional settings, yet their behaviors in common-law jury trials remain unexplored. We stud
arXiv:2609.09163v1 Announce Type: new Abstract: LLMs generalize across a domain only after seeing many real, labeled examples, which most domains lack. We study a way to manufacture it cheaply. When a
arXiv:2609.09677v1 Announce Type: new Abstract: Incremental-text streaming text-to-speech (TTS) needs online text progress tracking for synchronized highlighting, interruption handling, and dialogue-h
arXiv:2609.07125v1 Announce Type: new Abstract: This paper presents a novel framework designed to enhance key object identification in autonomous driving. Existing methods primarily focus on either de
arXiv:2609.07664v1 Announce Type: new Abstract: Deployment of Large Language Models (LLMs) on memory-constrained edge devices relies heavily on aggressive post-training quantization. However, evaluati
arXiv:2603.18074v2 Announce Type: replace Abstract: Technical-service LLM agents are entering production workflows, where value depends on whether engineers adopt generated replies. Service tickets hi
arXiv:2609.06978v1 Announce Type: new Abstract: Progress in video anomaly understanding (VAU) has long been limited by inherent deficiencies of real-world anomaly videos, which are hard to collect and
Another banger paper from Google. If you build memory for long-horizon agents, this one is worth your time. (bookmark it) Really nice to see how knowledge graphs are being explored in creative ways fo
arXiv:2609.07884v1 Announce Type: new Abstract: Recent work, such as Vision Banana, shows that lightweight instruction tuning can enable an image generator to achieve state-of-the-art performance acro
Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaP
arXiv:2609.07943v1 Announce Type: cross Abstract: There is significant uncertainty about whether abstractions like beliefs or desires usefully describe the behavior of large language models (LLMs). In
arXiv:2609.05937v1 Announce Type: new Abstract: Vision Transformers (ViTs) have shown immense potential in medical image analysis. However, standard pre-training via global image classification suffer
arXiv:2609.08220v1 Announce Type: new Abstract: Large language models (LLMs) have recently emerged as a promising tool for automating robot design from high-level specifications, yet they remain ineff
arXiv:2609.06504v1 Announce Type: new Abstract: Memory facilitates question answering over long videos by extracting and retrieving facts to fit within the limited context windows of multimodal LLMs (
arXiv:2609.05575v1 Announce Type: cross Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability
arXiv:2609.08419v1 Announce Type: new Abstract: Multiple Instance Learning (MIL) is widely used for weakly supervised learning, particularly in digital pathology, where fine-grained annotations are co
arXiv:2609.08638v1 Announce Type: new Abstract: An action chunk can span several stages of a manipulation task, yet a label for its first step describes only the current stage. We introduce Chunk-Alig
arXiv:2609.06721v1 Announce Type: new Abstract: AI companions are envisioned as always-on assistants that support users in daily life. With this regard, we introduce BuddyVQA, a benchmark for companio
arXiv:2609.08999v1 Announce Type: new Abstract: Partially Relevant Video Retrieval (PRVR) retrieves untrimmed videos when queries describe only short moments. Although recent methods improve local rep
Congratulations to Tristan Buckmaster and Levent Alpöge for developing the AI assisted techniques for solving an important math problem. Congratulations to OpenAI for not letting any good customer tra
arXiv:2609.07070v1 Announce Type: new Abstract: Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete
arXiv:2609.06704v1 Announce Type: new Abstract: Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the
arXiv:2609.07499v1 Announce Type: new Abstract: Training-free collaborative pipelines that integrate Vision Foundation Models such as CLIP, SAM, and DINO achieve strong open-vocabulary dense predictio
arXiv:2609.07685v1 Announce Type: new Abstract: In real-world applications, pedestrian trajectory prediction models rely on inputs from detection and tracking systems. Prior trajectory prediction benc
Learn how to deploy Qwen3.8-2.4T-A95B, a 2.4-trillion-parameter open-weight model, on Amazon SageMaker HyperPod with vLLM. This walkthrough covers cluster provisioning, NVFP4 quantization, and an Open
arXiv:2609.08337v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers teacher knowledge on student-generated trajectories, but efficient sampled objectives reduce the teacher distribu
arXiv:2609.05525v1 Announce Type: new Abstract: Large vision-language models (VLMs) are increasingly deployed in safety-critical settings, yet existing visual jailbreak research has focused almost exc
arXiv:2609.08331v1 Announce Type: new Abstract: Video Large Language Models (VideoLLMs) are increasingly deployed in safety-critical applications such as content moderation and video analytics. To pro
arXiv:2609.05842v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards enables large language models to think slowly, but the same training can induce policy collapse: probab
im new to using ai so i may be missing something. I set up ollama but dont want any of my data to go to any of the model providers, for certain models i appear to need an api key to download the model
Just a reminder for those out there itching to get into local llms - don't let FOMO or 'gear acquisition syndrom' take over. No matter the hobby, it's so easy to get stuck in a trap where we buy more
arXiv:2609.08282v1 Announce Type: new Abstract: Unified multimodal models integrate visual understanding and generation within a single network, yet the two capabilities are commonly optimized as sepa
arXiv:2609.08164v1 Announce Type: new Abstract: Aerial Object Goal Navigation (ObjectNav) requires an unmanned aerial vehicle (UAV) to locate a described target in an unknown outdoor environment using
arXiv:2609.08805v1 Announce Type: new Abstract: Preoperative evaluation of trigeminal neuralgia (TN) often requires joint interpretation of structural MRI, which depicts the trigeminal nerve and surro
arXiv:2609.06073v1 Announce Type: new Abstract: Federated fine-tuning adapts large language models (LLMs) to decentralized client data, but its scalability in cross-device training is often limited by
I have been a dwarfstar fan for awhile and I really liked glm 5.3 flash but needed it to be materially faster to feel good using it. In the screenshot you can see the outcome of using the model with a
arXiv:2609.09082v1 Announce Type: new Abstract: Open vocabulary 3D semantic segmentation methods typically lift CLIP features into 3D. This embeds points in a joint vision-language space known to beha
arXiv:2609.05582v1 Announce Type: new Abstract: Personalization can improve activity-recognition performance, but participant-specific gains are heterogeneous, and every additional calibration label h
arXiv:2412.09529v4 Announce Type: replace Abstract: Radiology, with its heterogeneous modalities, anatomies, and evolving protocols, is a natural yet high-stakes testbed for agentic AI. As LLMs grow m
arXiv:2505.21465v2 Announce Type: replace Abstract: Currently, a prevalent approach for enhancing Vision-Language Models (VLMs) performance is to encode both the high-resolution version and the thumbn
If they truly believe the risk is that high, and I think they do, then we need 100x more research and understanding of it. That requires them to openly share their models, datasets, training code, and
arXiv:2609.08755v1 Announce Type: new Abstract: Many emerging video language modeling tasks require systems to move beyond clip-level abstraction and model visual content as it unfolds over extended t
arXiv:2609.06578v1 Announce Type: new Abstract: World Action Models (WAMs) extend Vision-Language-Action (VLA) models by incorporating future visual dynamics into action generation. However, existing
arXiv:2609.09009v1 Announce Type: new Abstract: Denoising Diffusion Probabilistic Models (DDPMs) generate samples by starting from noise and repeatedly denoising while keeping each update close to the
arXiv:2609.08841v1 Announce Type: new Abstract: High-fidelity vehicle assets are essential for controllable traffic scene generation, particularly for synthesizing rare and safety-critical long-tail s
arXiv:2609.06341v1 Announce Type: new Abstract: Linear algebra provides the framework of concepts (matrix rank, singular value decomposition (SVD), and eigendecomposition) that modern artificial intel
arXiv:2609.07303v1 Announce Type: new Abstract: Current paradigms for training language models via reinforcement learning rely heavily on sparse outcome rewards. However, as we pursue tasks that requi
The 256th episode of the LWiAI Podcast (recorded 09/03/2026) discusses major AI developments from the prior week: Anthropic’s Claude Fable 5.1 and Mythos 5.1, which feature lower pricing, stronger age
arXiv:2609.07966v1 Announce Type: new Abstract: Key--value (KV) cache compression is an effective way to reduce the memory overhead of large language model (LLM) inference, particularly for long-conte
From the email 'Early access to new models During the program, approved users can try two next-generation Xiaomi MiMo models for a limited time: MiMo-X-Pro-Preview and MiMo-X-Flash-Preview. The MiMo-X
arXiv:2609.08958v1 Announce Type: new Abstract: Tensegrity robots offer lightweight, compliant mobility over challenging terrain but remain difficult to model and control due to complex contact-rich d
arXiv:2609.08663v1 Announce Type: new Abstract: Universal multimodal embedding (UME) increasingly demands encoder's capacity for handling a broad range of tasks and modalities with increased complexit
arXiv:2609.06373v1 Announce Type: new Abstract: Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across shots. Existing video generators f
arXiv:2609.08130v1 Announce Type: new Abstract: Driver alerting from dashcam video requires sequential decision-making under partial observability: a system must decide not only whether a scene is ris
arXiv:2609.08977v1 Announce Type: cross Abstract: In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic capabilities within a single fram
arXiv:2609.05885v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) has become the standard for parameter-efficient fine-tuning of large language models. Most LoRA variants follow a uniform-LR
arXiv:2609.06629v1 Announce Type: new Abstract: Recent advancements in deep learning allow robotic agents to interact with dynamic and unstructured environments. Of special interest is the integration