Knowledge catalogue
arXiv:2605.22597v1 Announce Type: cross Abstract: Learning real-world dynamics from visual observations is crucial for various domains. A common strategy is to calibrate simulators by estimating physi
arXiv:2605.21852v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in general video understanding, their capacity to interpret invo
arXiv:2605.22675v1 Announce Type: new Abstract: Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signal
arXiv:2605.22283v1 Announce Type: new Abstract: We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly ass
arXiv:2601.20107v2 Announce Type: replace-cross Abstract: Recent Vision-Language Models (e.g., ColPali) enable fine-grained Visual Document Retrieval (VDR) but incur prohibitive multi-vector index sto
arXiv:2605.22217v1 Announce Type: cross Abstract: Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent s
arXiv:2605.21976v1 Announce Type: new Abstract: Vision-based learning from demonstrations has achieved remarkable success in enabling robots to perform manipulation tasks and high-level semantic reaso
Gary Marcus discusses the current state of large language models (LLMs), likely covering their capabilities, limitations, and practical applications in AI. The post probably addresses key challenges s
This week, we shipped @QodoAI Findings. It's the natural next step from PR-by-PR review. Here's the problem it solves. If you manage an engineering team right now, you can probably answer a question a
arXiv:2601.05106v4 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a singl
arXiv:2605.22414v1 Announce Type: new Abstract: Visual Question Answering (VQA) holds great promise for clinical support, particularly in ophthalmology, where retinal fundus photography is essential f
arXiv:2603.28103v2 Announce Type: replace-cross Abstract: Parliamentary proceedings represent a rich yet challenging resource for computational analysis, particularly when preserved only as scanned hi
arXiv:2605.22403v1 Announce Type: new Abstract: Surface electromyography (sEMG) signal-based activity recognition has attracted increasing research attention in recent years. To develop accurate sEMG
arXiv:2605.20742v1 Announce Type: new Abstract: With the rapid proliferation of electric vehicles, the safety and reliability of lithium-ion batteries have become critical concerns. Effective anomaly
arXiv:2605.21924v1 Announce Type: new Abstract: On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. W
arXiv:2605.22651v1 Announce Type: new Abstract: CLIP-style contrastive pretraining typically curates web-scale image-text pairs using sample-level filtering signals, often based on pair-level alignmen
arXiv:2503.02885v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have gained traction in educational settings, often framed as virtual tutors or teaching assistants. Following ea
arXiv:2605.20666v1 Announce Type: new Abstract: This paper proposes a new birth model including semantic information derived from deep learning to create an occlusion-aware Gaussian Mixture Probabilit
Automated code quality and security heavyweight SonarSource Sàrl said today it’s buying a rival startup called Gitar Inc. that specializes in artificial intelligence-native code reviews. According to
As of yesterday, we made everyone within @llama_index research/engineering/product a Member of Technical Staff. Yes all the frontier labs have done this for years. But we didn’t only make these change
arXiv:2602.08819v2 Announce Type: replace-cross Abstract: Reward models are central to aligning language models with human preferences via reinforcement learning (RL). As RL is increasingly applied to
arXiv:2605.21027v1 Announce Type: new Abstract: Enterprise analytics aims to make organizational data accessible for decision-making, yet non-technical users still face barriers when using traditional
arXiv:2605.21177v1 Announce Type: cross Abstract: This work presents extsc{ChunkFT}, a memory-efficient fine-tuning framework that reformulates full-parameter fine-tuning around a dynamically activate
arXiv:2605.20473v1 Announce Type: cross Abstract: Test-time scaling has emerged as a promising approach for improving code generation by exploring large solution spaces at inference time. However, exi
arXiv:2605.20555v1 Announce Type: new Abstract: We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Gr
arXiv:2605.20247v1 Announce Type: cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mi
Cursor's new Composer 2.5 takes third on the Artificial Analysis Coding Agent Index and is ~10-60x lower cost than the higher-effort Opus 4.7 and GPT-5.5 variants above it. This release puts Composer
arXiv:2601.22932v2 Announce Type: replace Abstract: We study a sampling problem whose target distribution is pi propto exp(-f-r) where the data fidelity term f is Lipschitz smooth while the regularize
arXiv:2605.20369v1 Announce Type: new Abstract: Number prediction stands as a fundamental capability of large language models (LLMs) in mathematical problem-solving and code generation. The widely ado
arXiv:2605.20576v1 Announce Type: new Abstract: Inferring rigid-body physical states and properties from monocular videos is a fundamental step toward physics-based perception and simulation. Existing
arXiv:2605.20382v1 Announce Type: new Abstract: Language models are trained to follow instructions, but they are also powerful pattern completers. What happens when these two objectives conflict? We c
arXiv:2605.20448v1 Announce Type: new Abstract: Vision--language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-c
arXiv:2605.20254v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research attention, bec
arXiv:2502.18915v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, they are of
For anyone who isn't sure, this is how you release a model and talk about the performance. Not 3-5 cherry-picked benchmarks. Performance：Qwen3.7-Max performs strongly across benchmarks in coding agent
arXiv:2605.20892v1 Announce Type: new Abstract: Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-qu
arXiv:2605.20287v1 Announce Type: cross Abstract: Standard cells form the building blocks of digital circuits, so their delay and power critically influence chip-level performance; yet characterizatio
FWIW, I think this moves up my AI timelines a bit. I think the next milestone will be 'Artificial *Grothendieck* Intelligence' (AGrI): defining new general mathematical structures to solve the hardest
Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Gated DeltaNet-2 outperforms KDA and Mamba-3, the latest and best recurrent architectures, hea
arXiv:2605.21076v1 Announce Type: new Abstract: Grading German legal exam solutions faces growing volumes and a shortage of qualified graders, delaying feedback and creating a bottleneck. At the same
He's right. And it has a direct implication for code review that nobody's talking about. Think about why AI cracked coding before almost everything else. Not because code is simple. Because code is ch
arXiv:2605.20725v1 Announce Type: new Abstract: Learning with noisy labels in multimedia classification often combines external annotations and model predictions into a single reliability weight, even
I called my engineer friend at SpaceX the other day. 1am Pacific. 3am in Starbase. He was still in the office and not going home any time soon. And he was happy. Energized. Because he's directly influ
arXiv:2605.20648v1 Announce Type: new Abstract: Learning from Demonstration (LfD) enables robots to learn complex behaviors from expert examples, yet existing approaches often fail to generalize to ne
arXiv:2605.20242v1 Announce Type: new Abstract: Efficient discovery of precursor additives is essential for improving the performance of perovskite solar cells, yet the large chemical space makes conv
arXiv:2602.06025v2 Announce Type: replace Abstract: Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offl
arXiv:2605.20314v1 Announce Type: new Abstract: This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a large
arXiv:2605.20211v1 Announce Type: new Abstract: Educational videos are a cornerstone of remote and blended learning. However, learners' fluctuating attention remains a significant barrier to effective
arXiv:2605.20525v1 Announce Type: cross Abstract: We present NeuroQA, a large-scale benchmark for visual question answering in 3D brain magnetic resonance imaging (MRI), with 56,953 QA pairs from 12,9
arXiv:2605.20818v1 Announce Type: new Abstract: In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 20
arXiv:2605.21414v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-languag
arXiv:2605.20195v1 Announce Type: new Abstract: A target-oriented proactive dialogue system is designed to steer conversations toward predefined targets while actively providing suggestions. The core
arXiv:2605.20584v1 Announce Type: new Abstract: Mobile app marketplaces require developers to disclose standardized content rating descriptors (CRDs) to inform users about potentially sensitive or res
arXiv:2605.20809v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable performance on zero-shot annotation tasks, they often struggle with the specialized convention
arXiv:2605.20277v1 Announce Type: new Abstract: Medical vision-language models (VLMs) have rapidly advanced as general-purpose multimodal assistants, yet their deployment in 3D Computed Tomography (CT
arXiv:2510.04905v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have significantly improved automated code generation. While existing approaches have achieved
arXiv:2605.20916v1 Announce Type: new Abstract: Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opini
arXiv:2605.21443v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing eval
arXiv:2509.07674v2 Announce Type: replace Abstract: Explainability, in particular, the ability for robots to explain why they have made a decision or behaved in a certain way, is a critical tool in he
Ten years ago, I walked into Tesla as an intern — January 2015, back when all we built was the Model S. I never imagined I'd one day lead the Fremont factory where we are building some of the most ama