Knowledge catalogue
arXiv:2607.12104v1 Announce Type: cross Abstract: Machine learning models for system diagnostics rely on kernel execution traces to capture fine-grained system behavior, but collecting production trac
arXiv:2607.12267v1 Announce Type: cross Abstract: Language agents that interleave reasoning and tool use degrade sharply as reasoning chains lengthen, even when each individual step is easy. We trace
arXiv:2607.11939v1 Announce Type: new Abstract: Accurate pedestrian trajectory prediction in crowded environments remains challenging due to the multimodal uncertainty of human motion and the variable
arXiv:2607.12856v1 Announce Type: new Abstract: Buildings are expected to shift cooling loads in response to grid conditions. Thermal energy storage (TES) enables this shift, but scheduling it well re
arXiv:2512.15748v2 Announce Type: replace-cross Abstract: Visual Species Recognition (VSR) is a fundamental task in scientific disciplines that require species-level identification, including ecology,
arXiv:2510.20963v2 Announce Type: replace Abstract: Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multiple large language models (LLMs) to improve reasonin
Chinese models are now 41% of Hugging Face downloads. They passed the US. Clem Delangue @ClemDelangue, CEO of the main open model platform, cites Hugging Face's own Spring 2026 report: Chinese open we
Fable, turn my tweet into a thinkpiece (this was pretty funny): There has never been a better time to have opinions about artificial intelligence. I say this with some authority, because I am currentl
Highly-recommended overview of metacognition in LLMs. (bookmark it) Interesting behaviors in LLMs like confidence calibration, self-verification, knowing when to stop, and knowing what you do not know
I want to have this in writing so I can refer back to this tweet before it inevitably becomes a consensus view on twitter and say 'I told you so!' - The mass majority of researchers and academics in d
This post shows how Thrad.ai deployed a multi-agent system with Strands Agents and Amazon Bedrock AgentCore that automates the pipeline from prospect discovery through personalized email generation. T
Apple Music serves listeners across 150+ storefronts in dozens of languages, with a catalog that grows by hundreds of thousands of new tracks daily. At this scale, search recall on misspelled, transli
some good self improvement research here The first experimental evidence of recursive self-improvement (RSI). Autoresearching the autoresearch agent for eight days. The result beats the harness we han
Big unlock for open-source AI inference: Hugging Face Transformers models can now run in vLLM at native speed, often matching or beating hand-written implementations. Until now, every new architecture
congrats on the launch! As the task horizons on agents gets longer, we need more work evaluating and training models to be better in long-running, open-ended, evolving real-world environments. Today w
New model for AMD Strix Halo users: My 198B Step 3.7 Flash release was a big hit, but this one may be even better: 298B-parameter Hy3, now running on a new 2-bit FPX codebook designed to map efficient
Today we present Morpheus, a persistent enterprise simulation platform designed to make Continual Learning a reality. Morpheus is the world’s first real world Reinforcement Learning environment. Every
playing with local AI models and doing some research and came across a fun extrapolation: 'consumer grade graphics cards will be running Fable-equivalent models by 2029' the argument: 1) been said tha
Grok 4.5 is an AI language model developed by xAI, featuring improvements in reasoning, coding, and multimodal capabilities compared to earlier versions. The model demonstrates enhanced performance ac
arXiv:2607.08690v1 Announce Type: cross Abstract: Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft tokens which are then verified in para
arXiv:2607.07761v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care. This surv
arXiv:2607.08741v1 Announce Type: cross Abstract: Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While rece
arXiv:2607.08397v1 Announce Type: new Abstract: Referring Image Segmentation (RIS) aims to segment image regions specified by natural language, enabling fine-grained and controllable visual understand
arXiv:2607.08107v1 Announce Type: cross Abstract: Two-tower retrievers compress each user into a single embedding, limiting their ability to serve diverse interests. Multi-interest models give each us
arXiv:2606.12886v2 Announce Type: replace-cross Abstract: Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatia
arXiv:2607.08117v1 Announce Type: new Abstract: Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entitie
arXiv:2607.08497v1 Announce Type: cross Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, t
arXiv:2607.07729v1 Announce Type: cross Abstract: As foundation models grow in scale and diversity, coordinating multiple models into cooperative reasoning systems offers a path toward safer, more rel
arXiv:2503.12999v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have demonstrated exceptional performance in various multi-modal tasks. Recently, there has been an increasing i
arXiv:2607.08499v1 Announce Type: new Abstract: We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trai
arXiv:2607.08150v1 Announce Type: new Abstract: Symbolic regression (SR) discovers analytical equations from data, yielding glass-box models with directly interpretable formulas, unlike black-box meth
arXiv:2607.08434v1 Announce Type: new Abstract: Current Unified Large Multimodal Models (ULMMs) support interleaved multimodal reasoning through textual reasoning and intermediate visual states, but t
arXiv:2606.17093v2 Announce Type: replace Abstract: Learning-based single-shot fringe projection profilometry (FPP) has been studied almost entirely at close range, and the networks used are evaluated
arXiv:2607.08194v1 Announce Type: new Abstract: Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requi
arXiv:2607.08674v1 Announce Type: new Abstract: The rapid advancement of generative AI has enabled the creation of highly realistic deepfake media, posing significant threats, including misinformation
arXiv:2607.08642v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by drafting several tokens and verifying them in parallel. Block-diffusion drafters such as DFlash produc
arXiv:2601.10504v2 Announce Type: replace Abstract: As Large Language Models (LLMs) increasingly operate as Deep Research (DR) Agents capable of autonomous investigation and information synthesis, rel
arXiv:2504.07856v4 Announce Type: replace Abstract: Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dime
arXiv:2607.08362v1 Announce Type: new Abstract: Vietnam's ethnic minority languages are almost absent from the field of Natural Language Processing (NLP), and the challenge goes beyond data scarcity:
arXiv:2607.07918v1 Announce Type: cross Abstract: Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Late
arXiv:2607.08493v1 Announce Type: cross Abstract: Subjective NLP tasks often exhibit systematic annotator disagreement, requiring models that represent uncertainty rather than collapse it. We introduc
arXiv:2607.08092v1 Announce Type: cross Abstract: Privacy-preserving clustering is critical for analyzing sensitive data in healthcare, cybersecurity, and enterprise applications, where maintaining da
arXiv:2607.08575v1 Announce Type: new Abstract: We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation. FabriVLA combines an InternVL3.5 vision-language ba
arXiv:2607.08368v1 Announce Type: new Abstract: With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of
arXiv:2607.08009v1 Announce Type: new Abstract: We introduce a Bloom-aligned framework for measuring educational control in Large Language Models (LLMs): the ability to preserve a task's instructional
arXiv:2607.07881v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security vulnerabilities
arXiv:2607.08403v1 Announce Type: new Abstract: The application of lightweight Large Language Models in rule-based scientific domains remains severely limited by their tendency to mimic linguistic pat
arXiv:2607.08769v1 Announce Type: new Abstract: Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisition and computation. Adopting panoramic images with equirect
arXiv:2511.18940v3 Announce Type: replace Abstract: Cross-subject motor imagery decoding remains a fundamental challenge in EEG-based brain-computer interfaces due to substantial inter-subject variabi
arXiv:2412.07259v5 Announce Type: replace Abstract: DatalogMTL is a powerful rule-based language for temporal reasoning. Due to its high expressive power and flexible modeling capabilities, it is suit
arXiv:2602.08417v2 Announce Type: replace Abstract: Map-based LiDAR pose tracking is essential for long-term autonomous operation, where onboard map priors need be compact for scalable storage and fas
arXiv:2607.07993v1 Announce Type: new Abstract: Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work rel
arXiv:2601.22448v2 Announce Type: replace-cross Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cos
arXiv:2607.07754v1 Announce Type: new Abstract: Pattern recognition problems arise in a variety of physical image processing situations, and convolutional neural networks are a popular scheme for the
arXiv:2607.07740v1 Announce Type: cross Abstract: Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workfl
arXiv:2607.08392v1 Announce Type: cross Abstract: Amortized neural inverse design typically remains closed-world: component choices are fixed vocabulary tokens, coordinate grids are frozen at training
arXiv:2607.08735v1 Announce Type: new Abstract: Modern robotic perception increasingly involves large-scale geometric optimization problems distributed across multiple robots or sessions. However, exi
arXiv:2607.08182v1 Announce Type: cross Abstract: Vision-language-action (VLA) models aim to map multimodal inputs to robot actions. However, most existing approaches struggle to cover complex dynamic
arXiv:2603.12478v2 Announce Type: replace Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is
arXiv:2604.01388v2 Announce Type: replace Abstract: Recent advancements in open-vocabulary 3D scene understanding heavily rely on 3D Gaussian Splatting (3DGS) to register vision-language features into