Knowledge catalogue
arXiv:2602.11698v2 Announce Type: replace Abstract: Recursive (looped) Transformers decouple computational depth from parameter depth by repeatedly applying shared layers, providing an explicit archit
arXiv:2604.17880v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have achieved great success on general robotic tasks, but still face challenges in fine-grained spatiotemporal man
arXiv:2601.07155v2 Announce Type: replace Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however,
arXiv:2604.17887v1 Announce Type: new Abstract: Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy executio
arXiv:2604.18401v1 Announce Type: new Abstract: General agents have given rise to phenomenal applications such as OpenClaw and Claude Code. As these agent systems (a.k.a. Harnesses) strive for bolder
arXiv:2602.11528v2 Announce Type: replace-cross Abstract: Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generate
arXiv:2604.17830v1 Announce Type: new Abstract: Traditional Task and Motion Planning (TAMP) systems depend on physics models for motion planning and discrete symbolic models for task planning. Althoug
arXiv:2604.17159v1 Announce Type: cross Abstract: We present, to our knowledge, the most comprehensive cross-model evaluation of LLM agents on offensive cybersecurity tasks, benchmarking 10 frontier m
arXiv:2604.18573v1 Announce Type: new Abstract: Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, whi
arXiv:2511.17408v4 Announce Type: replace-cross Abstract: Probing has emerged as a promising method for monitoring large language models (LLMs), enabling cheap inference-time detection of concerning b
arXiv:2507.01936v3 Announce Type: replace Abstract: Large language models (LLMs) are excellent at maintaining high-level, convincing dialogue, but it remains unclear whether their persuasive success r
They just indicted the Southern Poverty Law Center on 11 counts of fraud. Wow! The SPLC worked with Facebook, Old Twitter and Youtube on their safety teams, sometimes directly advising/flagging what c
OpenAI announced a live event showcasing new capabilities or features, likely including extended thinking, content generation, and livestreaming functionalities. The event demonstrated how these featu
arXiv:2604.17648v1 Announce Type: new Abstract: Summarizing deeply nested discussion threads requires handling interleaved replies, quotes, and overlapping topics, which standard LLM summarizers strug
arXiv:2603.08096v3 Announce Type: replace Abstract: Localizing objects and parts from natural language in 3D space is essential for robotics, AR, and embodied AI, yet existing methods face a trade-off
arXiv:2604.17480v1 Announce Type: new Abstract: In principle, deep generative models can be used to perform domain adaptation; i.e. align the input feature representations of test data with that of a
arXiv:2405.13068v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have revolutionized various applications, making robust safety alignment essential to prevent harmful outputs. Cu
arXiv:2604.17472v1 Announce Type: new Abstract: Recent advances in 3D vision have led to specialized models for either 3D understanding (e.g., shape classification, segmentation, reconstruction) or 3D
arXiv:2506.00065v2 Announce Type: replace Abstract: Multimodal language models (MLMs) increasingly demonstrate human-like communication, yet their use of everyday perspectival words remains poorly und
arXiv:2604.17318v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, pos
arXiv:2601.04043v2 Announce Type: replace Abstract: As Multimodal Large Language Models (MLLMs) become an indispensable assistant in human life, the unsafe content generated by MLLMs poses a danger to
arXiv:2604.17375v1 Announce Type: new Abstract: Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning tem
Whistant is an on-phone AI buddy that helps users get things done directly from their iPhone without requiring a Mac. It breaks requests into step-by-step subtasks and executes them on the device, inc
arXiv:2604.18478v1 Announce Type: cross Abstract: Persistent memory is the bottleneck separating stateless chatbots from long-running agentic systems. Retrieval-augmented generation (RAG) over flat ve
arXiv:2604.17949v1 Announce Type: new Abstract: Deep learning-based industrial anomaly detectors often behave as black boxes, making it hard to justify decisions with physically meaningful defect evid
arXiv:2604.15453v1 Announce Type: cross Abstract: Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, token
arXiv:2604.15958v1 Announce Type: cross Abstract: Despite the considerable promise of Retrieval-Augmented Generation (RAG), many real-world use cases may create privacy concerns, where the purported u
“AI is at best a functional mimic, not a conscious experiencing subject. …. The real moral issue lies not in making AI conscious …. but in avoiding transforming humans into zombies” @GaryMarcus @OEIAC
arXiv:2510.24328v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal co
arXiv:2604.16217v1 Announce Type: cross Abstract: Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilitie
arXiv:2604.15503v1 Announce Type: new Abstract: Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language
arXiv:2604.15675v1 Announce Type: new Abstract: Achieving cultural alignment in Large Language Models (LLMs) increasingly depends on synthetic data generation. For such synthesis, the most vital initi
arXiv:2604.16132v1 Announce Type: cross Abstract: Firearm violence is a pressing public health issue, yet research into survivors' lived experiences remains underfunded and difficult to scale. Qualita
arXiv:2602.05523v2 Announce Type: replace-cross Abstract: Agentic large language models (LLMs) are increasingly evaluated on cybersecurity tasks using capture-the-flag (CTF) benchmarks, yet existing p
arXiv:2512.05717v3 Announce Type: replace-cross Abstract: The past few years have seen the development of ``universal'' machine-learning interatomic potentials (uMLIPs) capable of approximating the gr
arXiv:2604.15748v1 Announce Type: new Abstract: Recently impressive performance has been achieved in Concept Bottleneck Models (CBM) by utilizing the image-text alignment learned by a large pre-traine
arXiv:2603.08899v2 Announce Type: replace Abstract: Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to
arXiv:2512.01099v2 Announce Type: replace Abstract: As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform compl
arXiv:2604.15456v1 Announce Type: new Abstract: Trustworthiness and transparency are essential for the clinical adoption of artificial intelligence (AI) in healthcare and biomedical research. Recent d
arXiv:2604.16099v1 Announce Type: new Abstract: Tables condense key transactional and administrative information into compact layouts, but practical extraction requires more than text recognition: sys
arXiv:2604.15750v1 Announce Type: cross Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive language generation due to their potential for parallel dec
arXiv:2604.15839v1 Announce Type: new Abstract: Most ATP benchmarks embed the final answer within the formal statement -- a convention we call 'Easy Mode' -- a design that simplifies the task relative
arXiv:2510.21977v2 Announce Type: replace Abstract: Large language models (LLMs) offer a promising way to simulate human survey responses, potentially reducing the cost of large-scale data collection.
EDINET-Bench is a benchmark dataset that evaluates large language models on complex financial analysis tasks using Japanese financial statements from the EDINET database. The benchmark tests LLM capab
arXiv:2604.15588v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into scientific workflows presents exciting opportunities to accelerate biomedical discovery. However,
arXiv:2604.15841v1 Announce Type: new Abstract: While large language models (LLMs) have achieved remarkable success in general language tasks, their performance on Chouxiang Language, a representative
arXiv:2505.21072v4 Announce Type: replace Abstract: Large Language Models (LLMs) enhanced with retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in
arXiv:2604.16298v1 Announce Type: new Abstract: UAV vision-language navigation (VLN) requires an agent to navigate complex 3D environments from an egocentric perspective while following ambiguous mult
arXiv:2604.15488v1 Announce Type: cross Abstract: Large language models (LLMs) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offer
arXiv:2604.15395v1 Announce Type: new Abstract: Over the recent years, the field of robotics has been undergoing a transformative paradigm shift from fixed, single-task, domain-specific solutions towa
arXiv:2506.19840v2 Announce Type: replace Abstract: Large-scale pre-trained video diffusion models have exhibited remarkable capabilities in diverse video generation. However, existing solutions face
Getting LLMs to simulate “true” randomness or generate diverse outputs is surprisingly difficult. We found a simple prompting trick that solves this by having the model generate and manipulate a rando
arXiv:2604.15495v1 Announce Type: new Abstract: Navigating complex, densely packed environments like retail stores, warehouses, and hospitals poses a significant spatial grounding challenge for humans
This newsletter covers three main topics: advances in automating alignment research to improve AI safety processes, a safety evaluation study of a Chinese AI model, and technical details about HiFloat
arXiv:2510.21934v3 Announce Type: replace Abstract: Risk assessment tools in healthcare commonly employ point-based scoring systems that map patients to ordinal risk categories via thresholds. While e
arXiv:2604.15741v1 Announce Type: cross Abstract: Uncertainty estimation is a promising approach to detect hallucinations in large language models (LLMs). Recent approaches commonly depend on model in
literally my basic model since 1998. crazy that some people still haven’t figured this out. My basic model of capabilities: LLMs are good at problems similar to those that appear in their training dat
arXiv:2604.15508v1 Announce Type: cross Abstract: LLMbench is a browser-based workbench for the comparative close reading of large language model (LLM) outputs. Where existing tools for LLM comparison
arXiv:2603.22201v2 Announce Type: replace Abstract: Humanoid robots require diverse motor skills to integrate into complex environments, but bridging the kinematic and dynamic embodiment gap from huma
Moonshot AI today released Kimi-K2.6, the latest addition to its popular Kimi series of open-source large language models. The Chinese artificial intelligence startup says that the algorithm outperfor