Knowledge catalogue
arXiv:2512.12069v3 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating defenses that are both g
arXiv:2503.03480v4 Announce Type: replace Abstract: Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-w
arXiv:2604.17252v1 Announce Type: new Abstract: Recent advancements in large language models (LLMs) have enabled agents to tackle complex embodied tasks through environmental interaction. However, the
arXiv:2601.09515v2 Announce Type: replace Abstract: Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophist
arXiv:2604.16517v1 Announce Type: cross Abstract: Large vision-language models (VLMs) achieve strong performance on multimodal tasks but often suffer from hallucination and poor grounding in knowledge
arXiv:2406.06543v2 Announce Type: replace-cross Abstract: Deep learning has driven significant technological advancements, but its high energy consumption limits its use on battery-operated edge devic
arXiv:2601.06498v2 Announce Type: replace Abstract: Due to the limited generalization and interpretability of deep learning classifiers, The final vetting of rare celestial object candidates still rel
arXiv:2604.17068v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) enable parallel text generation by iteratively denoising a fully masked sequence, unmasking a subset of masked t
arXiv:2604.18177v1 Announce Type: new Abstract: Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight
arXiv:2604.17358v1 Announce Type: new Abstract: While recent Spoken Language Models (SLMs) have been actively deployed in real-world scenarios, they lack the capability to discern Third-Party Interrup
arXiv:2510.02025v4 Announce Type: replace Abstract: We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers
arXiv:2604.17551v1 Announce Type: new Abstract: Standard approaches to goal-conditioned reinforcement learning (GCRL) that rely on temporal-difference learning can be unstable and sample-inefficient d
arXiv:2510.09671v2 Announce Type: replace Abstract: Table Question Answering (TQA) aims to answer natural language questions about tabular data, often accompanied by additional contexts such as text p
arXiv:2604.18107v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) achieve remarkable performance in sequential decision-making but remain fragile to subtle environmental shifts, suc
arXiv:2601.14944v3 Announce Type: replace Abstract: LLMs are ubiquitous in modern NLP, and while their applicability extends to texts produced for democratic activities such as online deliberations or
arXiv:2604.17121v1 Announce Type: new Abstract: Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dyna
arXiv:2604.18124v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning method for large language models, with its effectiveness largely
arXiv:2604.17739v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a prevalent paradigm for training tool calling agents, which typically requires online interactive environments
arXiv:2604.18239v1 Announce Type: new Abstract: Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based objectives suppress the
arXiv:2604.17658v1 Announce Type: cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (MAS) enable complex problem-solving but introduce significant debugging challenges, characterize
arXiv:2604.16351v1 Announce Type: cross Abstract: Dense retrieval compresses texts into single embeddings ranked by cosine similarity. While efficient for recall, this interface is brittle for identit
arXiv:2604.18389v1 Announce Type: new Abstract: Prompt sensitivity, which refers to how strongly the output of a large language model (LLM) depends on the exact wording of its input prompt, raises con
arXiv:2602.09130v3 Announce Type: replace Abstract: Model compression is increasingly essential for deploying large language models (LLMs), yet existing comparative studies largely focus on pruning an
arXiv:2508.15815v3 Announce Type: replace Abstract: Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicit
arXiv:2505.23941v4 Announce Type: replace-cross Abstract: Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that helps them on downstream tasks but also may noto
arXiv:2512.01643v2 Announce Type: replace Abstract: Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an o
arXiv:2510.17795v3 Announce Type: replace Abstract: Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate exec
arXiv:2604.18484v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex
arXiv:2511.01188v2 Announce Type: replace Abstract: The rapid spread of fake news threatens social stability and public trust, highlighting the urgent need for its effective detection. Although large
arXiv:2604.15371v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult t
arXiv:2601.07160v2 Announce Type: replace Abstract: To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. Ho
arXiv:2602.11173v2 Announce Type: replace Abstract: Author response (rebuttal) writing is a critical stage of scientific peer review that demands substantial author effort. In practice, authors posses
arXiv:2604.15332v1 Announce Type: cross Abstract: Crash diagrams are essential tools in transportation safety analysis, yet their manual preparation remains time-consuming and prone to human variabili
Databricks announced an integration of its Delta Sharing technology with Adobe Experience Platform to enable seamless data exchange for marketing workflows. The integration facilitates agentic marketi
arXiv:2604.15840v1 Announce Type: new Abstract: Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and le
arXiv:2508.06094v4 Announce Type: replace Abstract: Constructed languages (conlangs) such as Esperanto and Quenya have played diverse roles in art, philosophy, and international communication. Meanwhi
arXiv:2507.16727v3 Announce Type: replace Abstract: Improving the reliability of large language models (LLMs) is critical for deploying them in real-world scenarios. In this paper, we propose extbf{De
arXiv:2604.15723v1 Announce Type: cross Abstract: The advent of handheld fundus imaging devices has made ophthalmologic diagnosis and disease screening more accessible, efficient, and cost-effective.
arXiv:2604.15327v1 Announce Type: cross Abstract: Universities are microcosms of urban ecosystems, with concentrated consumption patterns in food, transport, energy, and product usage. These environme
arXiv:2510.13220v2 Announce Type: replace Abstract: A fundamental limitation of current AI agents is their inability to learn complex skills on the fly at test time, often behaving like 'clever but cl
arXiv:2604.15672v1 Announce Type: cross Abstract: Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive
arXiv:2604.01608v2 Announce Type: replace Abstract: Multi-agent systems (MAS) tackle complex tasks by distributing expertise, though this often comes at the cost of heavy coordination overhead, contex
arXiv:2602.01566v2 Announce Type: replace Abstract: Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research o
arXiv:2604.16214v1 Announce Type: new Abstract: Understanding affective dynamics in real-world social systems is fundamental to modeling and analyzing human-human interactions in complex environments.
arXiv:2604.15602v1 Announce Type: new Abstract: Preference optimization is widely used to align Large Language Models (LLMs) with preference feedback. However, most existing methods train on a single
Human biological limits, like our tiny working memory and shallow calculation depth, are actually a feature. They force us to abstract, compress, intuit. If we had infinite resources, we would never h
Intelligence per picojoule, with @itsclivetime and @dylan522p (0:00) Intro (1:22) What is codesign? (2:49) Codesign example: Swish vs ReLU (4:22) Are DeepSeek papers codesign? (6:45) Predicting where
LLMs are “ good at math style problems, where you tell them A, B and C are true, and then ask them to figure out D [but] extremely bad at anything involving what I would call mature scholarship .. [so
arXiv:2604.15363v1 Announce Type: cross Abstract: Motivated behaviour relies on the brain's capacity to evaluate effort and reward. Dysregulation within these processes contributes to a spectrum of co
arXiv:2604.16054v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and
arXiv:2604.15483v1 Announce Type: new Abstract: We present a new robotic foundation model, called {pi}_{0.7}, that can enable strong out-of-the-box performance in a wide range of scenarios. {pi}_{0.7}
arXiv:2604.15780v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in real-world applications, but even aligned models such as Mistral and LLaVA still exhibit unsafe b
arXiv:2604.15577v1 Announce Type: cross Abstract: Consider an auto-regressive model that produces outputs x (e.g., answers to questions, molecules) each of which can be summarized by an attribute vect
arXiv:2604.15356v1 Announce Type: cross Abstract: Recent work on KV cache quantization, culminating in TurboQuant, has approached the Shannon entropy limit for per-vector compression of transformer ke
arXiv:2604.15771v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a foundational paradigm for grounding large language models in external knowledge. While adaptive re
Source: https://spectrum.ieee.org/boston-dynamics-spot-google-deepmind I break down stories like this every day in my free newsletter. Keep up with the latest in AI/Robotics in 5 min a day: https://ww
arXiv:2604.15416v1 Announce Type: cross Abstract: Sign-based optimization algorithms, such as SignSGD, have garnered significant attention for their remarkable performance in distributed learning and
arXiv:2604.15559v1 Announce Type: new Abstract: Recent work on subliminal learning demonstrates that language models can transmit semantic traits through data that is semantically unrelated to those t
arXiv:2604.16262v1 Announce Type: new Abstract: Recent advances in language models have substantially improved Natural Language Understanding (NLU). Although widely used benchmarks suggest that Large
arXiv:2604.15898v1 Announce Type: new Abstract: For around a decade, non-symbolic methods have been the option of choice when explaining complex machine learning (ML) models. Unfortunately, such metho