Knowledge catalogue
arXiv:2609.38647v1 Announce Type: new Abstract: Direct preference optimization (DPO) models binary preferences through a Bradley-Terry model with a common noise scale, without explicitly accounting fo
arXiv:2609.36915v1 Announce Type: cross Abstract: Aerial manipulators extend robotic manipulation into 3D workspaces that are difficult for ground-based robots to access, creating new opportunities fo
Last Week in AI #345 notes that Anthropic and OpenAI are in a close race to launch more capable but cheaper models this month: Anthropic unveiled Claude Opus 5.5 with stricter cybersecurity safeguards
arXiv:2609.37457v1 Announce Type: new Abstract: Enterprise artificial-intelligence agents increasingly call tools, modify infrastructure, and process protected data, creating a need to separate action
arXiv:2609.33522v1 Announce Type: cross Abstract: Manual visual inspection on assembly lines is a persistent manufacturing bottleneck: operator fatigue over extended shifts lowers defect-detection rat
Anthropic: Anthropic says GLM-5.3 can autonomously build end-to-end cyber exploits, like Claude Mythos Preview, but was released without robust safeguards against misuse — GLM-5.3 can develop working
arXiv:2609.32519v1 Announce Type: cross Abstract: Model steering can strengthen a target behavior while degrading other useful behaviors. We introduce Supervised Transcoder Replacement (STR) to reduce
arXiv:2609.31326v1 Announce Type: cross Abstract: Ordinal acne severity grading requires distinguishing visually similar neighboring grades while jointly weighing holistic facial appearance and locali
arXiv:2505.14368v3 Announce Type: replace-cross Abstract: Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to attacks that generate harmful or sensitive outputs. As open-sou
arXiv:2609.30383v1 Announce Type: new Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend i
Every week, I talk with founders who are building at an unbelievable pace. Teams are moving from inception to product-market fit faster than ever, with foundation models wired deeply into their core p
arXiv:2609.27275v1 Announce Type: new Abstract: Most autonomous-driving datasets record only the action executed by a behavior policy and the single future that followed, providing limited supervision
from FreedomIntelligence: HuatuoGPT-3-27B is a medical LLM built on Qwen3.8-27B with One-stage Policy Optimization (OnePO). OnePO adapts language models to medicine in a single reinforcement-learning
arXiv:2609.26891v1 Announce Type: new Abstract: Modern language-model agents are built around the extit{agent loop}, where the LLM is placed in an environment exposing a set of tools, and the LLM has
Scribd, Inc. is home to one of the world's largest collections of human-created content. Scribd’s products leverage one of the world's largest collections of human-created content and intelligent tool
arXiv:2609.26911v1 Announce Type: new Abstract: A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify intervention, because the rep
arXiv:2609.27449v1 Announce Type: new Abstract: Generalist robot manipulation policies have developed rapidly, yet their reliable evaluation remains challenging due to fundamental flaws in existing si
arXiv:2312.06632v2 Announce Type: replace Abstract: Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful substa
Introducing Qwen Intelligence, bringing personal intelligence within everyone's reach. 📱✨ It launches with three SOTA agents: 🥳 - Mobile Planner Agent: plans, decomposes & orchestrates complex tasks.
Standardizing independent evaluation, fairness, and interpretability for mechanism-informed generative AI in healthcare The post MLCommons Joins EU-Funded AIRIS Project to Build and Benchmark Next-Gen
arXiv:2609.22110v1 Announce Type: new Abstract: Background: Large language models (LLMs) can improve healthcare information delivery in low-resource settings but may produce inaccurate or culturally i
arXiv:2609.22157v1 Announce Type: cross Abstract: KV-cache eviction methods decide which tokens to keep but not whether to evict at all, so a benchmark mean can hide a class of inputs on which compres
arXiv:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Psy
arXiv:2609.21722v1 Announce Type: cross Abstract: Chinese social media has generated a vast and continually evolving lexicon of internet buzzwords whose meanings are often non-literal and deeply roote
arXiv:2602.00993v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving models increasingly benefit from large vision-language models for semantic understanding, yet safe and reliable
arXiv:2609.19524v1 Announce Type: new Abstract: Benchmark scores alone provide an incomplete basis for assessing the trustworthiness of modern artificial intelligence systems. Large language models (L
arXiv:2609.19892v1 Announce Type: cross Abstract: As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing
arXiv:2609.20123v1 Announce Type: new Abstract: Modern smart vehicles leverage multimodal sensors, ranging from high-bandwidth vision systems to low-rate physiological monitors, to provide personalize
🔥: “While AI comes with danger, we should be sceptical of any narrative that conveys inevitability around its trajectory. AI systems do not build their own data centres. They do not manufacture their
arXiv:2609.19144v1 Announce Type: cross Abstract: Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences because of their computational and me
arXiv:2609.18864v1 Announce Type: cross Abstract: Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unaut
arXiv:2609.17549v1 Announce Type: new Abstract: Cyberbullying (CB) is a complex social phenomenon characterized by repeated aggression, power imbalance, and multi-party interaction. Although large lan
arXiv:2609.17538v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for structured information extraction from documents, yet their behavior under realistic OCR noise re
arXiv:2609.16592v1 Announce Type: new Abstract: This paper presents an end-to-end approach for generating context-specific large language model (LLM) benchmark datasets by combining expert input with
Welcome to the first Cloud CISO Perspectives for September 2026. Today, Sandra Joyce shares the latest details on Google’s visibility into how attackers are using AI, and how we’re using AI to stop th
arXiv:2609.16614v1 Announce Type: cross Abstract: Speech-to-speech dialogue models increasingly support persona control, yet existing spoken role-playing benchmarks remain largely character-centric an
arXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property o
arXiv:2609.14987v1 Announce Type: cross Abstract: Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect promp
arXiv:2609.15726v1 Announce Type: cross Abstract: Tactile sensing provides contact information that can be difficult to infer from vision alone, but tactile hardware for dexterous hands has not conver
arXiv:2609.13534v1 Announce Type: new Abstract: We identify extbf{Harmfulness Propagation Dynamics (HPD)}: for harmful prompts, the projection of the last-token hidden state onto a learned harm direct
arXiv:2609.13287v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) achieve high decoding efficiency through block-parallel, arbitrary-order generation, making them attractive fo
arXiv:2609.13980v1 Announce Type: cross Abstract: Arabic large-language-model (LLM) evaluation has matured around Modern Standard Arabic (MSA): aggregated leaderboards such as the Open Arabic LLM Lead
arXiv:2609.14860v1 Announce Type: cross Abstract: Warning: This submission studies stereotypes and biases, and contains toxic and offensive examples, used for illustration purposes only. Fairness benc
arXiv:2609.15013v1 Announce Type: new Abstract: Guardrail models are classifiers deployed to screen malicious prompts and responses in LLM-based services. To meet latency constraints, many lightweight
arXiv:2609.14759v1 Announce Type: cross Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model s
arXiv:2609.14780v1 Announce Type: cross Abstract: Multi-tenant tools commonly accept a tenant identifier and validate it against the caller's entitlement. For a large language model (LLM) agent, that
arXiv:2509.19375v2 Announce Type: replace-cross Abstract: Large language models are increasingly used for clinical text classification, where overconfident misclassifications can directly affect patie
arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also int
arXiv:2609.12894v1 Announce Type: new Abstract: Estimating the 3D center of mass of unknown objects is challenging when grasping is infeasible, geometry is irregular, or mass distribution is uneven. W
Intelligence was yours. A founder’s intellectual property, business logic, differentiation, their intelligence, was once theirs alone. You built it, you owned it, and no tools/platform vendor stood be
arXiv:2609.12550v1 Announce Type: new Abstract: Quantized Mixture-of-Experts (MoE) services can hold several pre-materialized instances of one base model, but quantization damage varies sharply across
arXiv:2609.11393v1 Announce Type: new Abstract: Test-time adaptation has emerged as a lightweight alternative to costly post-training for improving the reasoning capabilities of Large Language Models
arXiv:2609.10992v1 Announce Type: new Abstract: The integration of Large Language Models into daily tasks relies on context-rich instructions, inevitably exposing sensitive user information. Current p
arXiv:2609.10962v1 Announce Type: cross Abstract: Studies of the Model Context Protocol (MCP) server ecosystem draw their samples in ways that quietly select for servers that work: reference sets, pop
Terence Tao / What's new: A group of 25 Fields Medal recipients says AI companies' push to solve mathematical problems as a benchmark is detrimental to the science of mathematics — I am proud to be am
metal : single-source fusion table + fusion debug rework (#28164) metal : rework fusion patterns into a single table All fusable op patterns for the Metal backend are now declared once in a fusion tab
arXiv:2609.10744v1 Announce Type: cross Abstract: Autoregressive language models can be used to transform a payload text into a stegotext of identical token length by preserving per-position rank info
arXiv:2609.10892v1 Announce Type: cross Abstract: When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls,
arXiv:2609.09754v1 Announce Type: new Abstract: As large language models are increasingly deployed as tool-augmented legal agents, they introduce agentic hallucinations where tool-call and reasoning e
arXiv:2609.10060v1 Announce Type: new Abstract: Existing bias auditing methods typically rely on model outputs, requiring costly benchmarks or judge models and potentially missing internal shifts that