Knowledge catalogue
arXiv:2607.04882v1 Announce Type: new Abstract: Clandestine tunneling beneath oil and gas pipelines enables fuel theft, smuggling, and sabotage, yet conventional monitoring detects damage only after a
arXiv:2607.05006v1 Announce Type: new Abstract: While various works address reflective symmetry understanding in 3D data and images, pixel-level semantic left-right prediction of in-the-wild images re
This release candidate introduces support for offloading the image GPU projection (mmproj) to an integrated GPU when using fit padding in Ollama's LLM processing, addressing technical improvements for
arXiv:2607.02893v1 Announce Type: cross Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width. We introdu
arXiv:2510.05681v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) have demonstrated remarkable performance in robot control. However, they remain fundamentally limited in
arXiv:2607.03118v1 Announce Type: new Abstract: We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation
arXiv:2607.03589v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as an alternative to Vision Transformers, yet most vision SSMs inherit directional token scanning from causal seq
arXiv:2407.11691v5 Announce Type: replace Abstract: We present VLMEvalKit: an open-source toolkit for evaluating large multi-modality models based on PyTorch. The toolkit aims to provide a user-friend
arXiv:2607.04738v1 Announce Type: cross Abstract: Reconstructing population dynamics is a central problem in the physical and data sciences. Often, the dynamics are modeled as a Wasserstein gradient f
arXiv:2607.02885v1 Announce Type: cross Abstract: Cognitive Behavioral Therapy (CBT) provides a structured framework for understanding a user's mental state by examining the interaction between cognit
arXiv:2607.04350v1 Announce Type: new Abstract: Online social media posts provide scalable signals for early depression screening, and recent studies mainly improve pre-classification evidence through
b9879 is a release build identifier in the llama.cpp project, a C/C++ implementation of Meta's LLaMA language models. This release likely contains bug fixes, performance improvements, and feature upda
Must-read research by Anthropic. Here is the simple explanation and why this is a big deal. We suspect LLMs perform 'internal reasoning'. But little is known or do good methods exist to understand it.
We have an awesome roster of creators already signed up for the @fal x @sequoia video hackathon, taking place July 17-19th. Reminder to register! Lots of workshops/tutorials to get your feet wet, and
Check out all the amazing work from our @SimonsFdn Collaboration on the Physics of Learning and Neural Computation (https://www.physicsoflearning.org/) presented at the main meeting of @ICMLconf #ICML
Here's a cool piece of LLM lore: the original scaling laws were wrong due to a bug, which probably led to a lot of wasted compute on oversized undertrained models 🫣 (and that was before we even starte
arXiv:2607.01693v1 Announce Type: new Abstract: These notes give a proof-oriented introduction to diffusion models from the viewpoint of sampling, tracing a single arc from classical sampling dynamics
arXiv:2607.02403v1 Announce Type: cross Abstract: Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost ju
arXiv:2607.01287v1 Announce Type: cross Abstract: Accompanying a group of humans is an essential aspect of developing human-like social cognition in robots. However, human groups typically do not foll
arXiv:2607.01372v1 Announce Type: cross Abstract: Gravitational Waves (GWs) represent the newest window of astronomy, furthering our understanding of compact objects like black holes and neutron stars
arXiv:2607.02104v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models
arXiv:2607.02182v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit remarkable reasoning capabilities, but their task-specific fine-tuning is notoriously plagued by overconfidence,
arXiv:2607.01272v1 Announce Type: cross Abstract: Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must
arXiv:2602.07267v2 Announce Type: replace Abstract: Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Ex
arXiv:2607.02195v1 Announce Type: new Abstract: General-purpose vision-language-action models benefit from large vision-language priors, but effective manipulation also requires anticipating action-re
arXiv:2607.02262v1 Announce Type: new Abstract: Reasoning Language Models (RLMs) have significantly improved performance on complex tasks by extending the reasoning chain. However, these chains are pr
arXiv:2506.06323v2 Announce Type: replace-cross Abstract: Model-free and reinforcement learning-based adaptive filtering methods are gaining traction for denoising in dynamic, non-stationary environme
arXiv:2607.02496v1 Announce Type: cross Abstract: Realistic traffic simulation requires agents that imitate logged behavior and can also be steered along interpretable axes. Such controllability enabl
arXiv:2607.02210v1 Announce Type: new Abstract: The evolution toward fully autonomous telecommunications networks (Autonomous Network Levels 4-5) requires AI/ML agents to make real-time network decisi
arXiv:2607.02037v1 Announce Type: cross Abstract: Autonomous surface vehicles vary widely in hydrodynamic and actuation characteristics, yet most controllers are designed for single-platform deploymen
arXiv:2607.02390v1 Announce Type: new Abstract: How can Large Language Models (LLMs) solve problems they currently cannot? Repeated sampling scales test-time compute but GPU cost grows linearly with a
arXiv:2607.01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims req
arXiv:2607.02088v1 Announce Type: new Abstract: We propose an improved Fourier Neural Operator (FNO) for modeling two-dimensional Rayleigh-Benard convection by predicting time increments instead of fu
arXiv:2607.02199v1 Announce Type: cross Abstract: Mutual information (MI)-inspired feature learning techniques are capable of generating low-dimensional embeddings that retain nonlinear dependence str
arXiv:2607.01741v1 Announce Type: cross Abstract: Reinforcement Learning (RL) is a sequential decision-making framework in which an agent learns optimal policies through interaction with an environmen
arXiv:2607.02020v1 Announce Type: new Abstract: Multimodal large language models must continually adapt to evolving tasks and domains, yet standard continual learning metrics mainly measure whether ol
arXiv:2607.01237v1 Announce Type: cross Abstract: Reasoning language models often generate long chain-of-thought (CoT), which accumulates a massive KV cache during the decoding phase and incurs high d
arXiv:2607.02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing g
arXiv:2508.05941v2 Announce Type: replace Abstract: Visuomotor policies trained via behavior cloning are vulnerable to covariate shift, where small deviations from expert trajectories can compound int
arXiv:2512.18368v2 Announce Type: replace Abstract: Scaling imitation learning to diverse multi-task robot manipulation remains challenging due to suboptimal demonstrations, behavioral multi-modality,
arXiv:2606.13723v2 Announce Type: replace-cross Abstract: Intersection-over-Union (IoU), as a pivotal metric for evaluating the spatial alignment between candidate proposals and ground-truth annotatio
arXiv:2607.01420v1 Announce Type: cross Abstract: As grounded QA systems are increasingly deployed in AI assistants, accurately attributing generated answers to evidence is critical for user trust and
arXiv:2607.01972v1 Announce Type: cross Abstract: Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic plan
arXiv:2607.02291v1 Announce Type: new Abstract: Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, yet this practice frequently results
arXiv:2607.02461v1 Announce Type: cross Abstract: Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make infe
arXiv:2607.01883v1 Announce Type: new Abstract: Code is the medium through which large language models generate structured artifacts: charts, scientific figures, vector graphics, CAD models, 3D scenes
arXiv:2607.01803v1 Announce Type: cross Abstract: Recent advances in 3D content generation from text or images have achieved impressive results, yet view inconsistency from 2D generators and the scarc
arXiv:2607.01480v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifi
arXiv:2607.02512v1 Announce Type: cross Abstract: Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking
arXiv:2607.01527v1 Announce Type: cross Abstract: Room embeddings derived from reverberant speech are often unreliable: speech content and recording degradation can alter the representation even when
arXiv:2607.02298v1 Announce Type: new Abstract: Autonomous drones are rapidly transforming modern warfare and civil applications alike. This paper presents the development of an integrated intelligent
arXiv:2607.02509v1 Announce Type: new Abstract: Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Althou
arXiv:2603.06001v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasing
arXiv:2607.01823v1 Announce Type: cross Abstract: Packet loss concealment (PLC) reconstructs audio packets that are missing at the receiver, usually with a trained model whose parameters remain fixed
arXiv:2607.01795v1 Announce Type: cross Abstract: Monitoring cognitive load during online learning could help instructors identify content that learners find difficult, but remote settings remove the
arXiv:2607.01774v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches,
arXiv:2607.02416v1 Announce Type: new Abstract: Natural Language Processing (NLP) has traditionally been published in its core disciplinary venues like ACL. However, advances in Large Language Models
arXiv:2512.01715v2 Announce Type: replace Abstract: Vision-language-action (VLA) models that generate continuous action chunks via flow matching lack an internal signal for judging whether a given pre
arXiv:2607.02507v1 Announce Type: new Abstract: LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly t
Together AI highlights the rapid growth of AI token consumption across multiple companies and teams, noting an increase from 30 billion tokens monthly to 400 trillion annually, with platforms like Cur