Knowledge catalogue
arXiv:2604.12086v1 Announce Type: new Abstract: Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often
arXiv:2604.12500v1 Announce Type: new Abstract: Specification gaming under Reinforcement Learning (RL) is known to cause LLMs to develop sycophantic, manipulative, or deceptive behavior, yet the condi
arXiv:2512.04585v3 Announce Type: replace Abstract: Segment Anything Model 3 (SAM3) advances open-vocabulary segmentation through promptable concept segmentation, enabling users to segment all instanc
arXiv:2604.12350v1 Announce Type: cross Abstract: Molecular property optimization is central to drug discovery, yet many deep learning methods rely on black-box scoring and offer limited control over
arXiv:2602.05791v2 Announce Type: replace Abstract: Learning-based whole-body controllers have become a key driver for humanoid robots, yet most existing approaches require robot-specific training. In
arXiv:2511.06341v2 Announce Type: replace Abstract: Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as n
arXiv:2604.11835v1 Announce Type: cross Abstract: Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of struc
arXiv:2604.12002v1 Announce Type: new Abstract: Current post-training methods in verifiable settings fall into two categories. Reinforcement learning (RLVR) relies on binary rewards, which are broadly
arXiv:2507.08977v4 Announce Type: replace-cross Abstract: Scientific modeling faces a tradeoff between the interpretability of mechanistic theory and the predictive power of machine learning. While ex
arXiv:2603.12583v2 Announce Type: replace Abstract: In this work, we propose a data-driven framework to design optimal haptic nudge feedback leveraging the learner's estimated skill to address the cha
So true. “Being right too soon is socially unacceptable” I remember reading this from Heinlein as a young man and it took experience for me to fully understand it. People and institutions will persist
arXiv:2604.12617v1 Announce Type: cross Abstract: The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL)
arXiv:2510.20093v2 Announce Type: replace-cross Abstract: Although recent advancements in diffusion models have significantly enriched the quality of generated images, challenges remain in synthesizin
arXiv:2604.12935v1 Announce Type: new Abstract: Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Des
arXiv:2604.12770v1 Announce Type: new Abstract: Editing human-written text has become a standard use case of large language models (LLMs), for example, to make one's arguments more appropriate for a d
arXiv:2604.12232v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs
arXiv:2604.12092v1 Announce Type: new Abstract: Behavior Trees (BTs) provide designers an intuitive graphical interface to construct long-horizon plans for autonomous systems. To ensure their correctn
arXiv:2604.12116v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as tool-augmented agents capable of executing system-level operations. While existing benchmarks
The front door to the internet hasn't changed -- but the person going through that door has changed from a human browsing 5 blue links, to an agent browsing a similar index in vastly different ways. A
arXiv:2604.12816v1 Announce Type: new Abstract: Implicit biases in both humans and large language models (LLMs) pose significant societal risks. Dual process theories propose that biases arise primari
arXiv:2510.09087v2 Announce Type: replace Abstract: Large language model (LLM) agents have shown remarkable progress in social deduction games (SDGs). However, existing approaches primarily focus on i
arXiv:2509.25758v2 Announce Type: replace Abstract: The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (S
This is what a black politician in South Africa said… “We will kill white women, we will kill white children, and we will even kill your pets' Violent language entering politics is a serious warning s
arXiv:2604.12736v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly in their mathem
arXiv:2410.03000v3 Announce Type: replace Abstract: Existing certified training methods can only train models to be robust against a certain perturbation type (e.g. l_infty or l_2). However, an l_inft
arXiv:2604.12133v1 Announce Type: new Abstract: Historical approaches to Table Representation Learning (TRL) have largely adopted the sequential paradigms of Natural Language Processing (NLP). We argu
arXiv:2602.02370v2 Announce Type: replace Abstract: Accurate histopathologic interpretation is key for clinical decision-making; however, current deep learning models for digital pathology are often o
arXiv:2604.12817v1 Announce Type: new Abstract: Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To im
arXiv:2603.05295v3 Announce Type: replace Abstract: We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible r
What happens when you systematically oversell the value of your product for years, while pretty much screwing society along the way? Eventually your customers figure it out. Surprisingly, people see A
arXiv:2604.12509v1 Announce Type: cross Abstract: Mobile Manipulation (MoMa) of articulated objects, such as opening doors, drawers, and cupboards, demands simultaneous, whole-body coordination betwee
arXiv:2604.12025v1 Announce Type: new Abstract: The Semantic Web standardizes concept meaning for humans and machines, enabling machine-operable content and consistent interpretation that improves adv
arXiv:2604.13001v1 Announce Type: new Abstract: The acquisition of high-quality, action-aligned demonstration data remains a fundamental bottleneck in scaling foundation models for dexterous robot man
arXiv:2604.09639v1 Announce Type: new Abstract: Artistic style transfer is well studied for images and videos, but extending it to multi-view 3D scenes remains difficult because stylization can disrup
arXiv:2604.09676v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key approach for enhancing reasoning in large language models (LLMs), yet scalable training is often hindered
arXiv:2604.10252v1 Announce Type: new Abstract: Reinforcement learning agent-based simulation (RL-ABS) has become an important tool for electricity market mechanism analysis and evaluation. In the mod
arXiv:2601.16399v5 Announce Type: replace Abstract: We study a structured bi-level optimization problem where the upper-level objective is a smooth function and the lower-level problem is policy optim
arXiv:2604.11709v1 Announce Type: new Abstract: Accurate and rapid structural damage assessment (SDA) is crucial for post-disaster management, helping responders prioritise resources, plan rescues, an
arXiv:2604.05142v2 Announce Type: replace Abstract: As artificial intelligence systems (AIs) become increasingly produced by recursive self-improvement, a form of evolution may emerge, with the traits
arXiv:2407.10953v5 Announce Type: replace Abstract: The Mutual Reinforcement Effect (MRE) describes a phenomenon in information extraction where word-level and sentence-level tasks can mutually improv
Byard Duncan / Bloomberg: A profile of BusPatrol, whose AI-powered cameras on 35K+ school buses in 24 US states record vehicles passing illegally, claiming they help reduce violations — BusPatrol says
arXiv:2604.11125v1 Announce Type: new Abstract: India generates vast biomedical data through postgraduate research, government hospital services and audits, government schemes, private hospitals and t
arXiv:2604.10427v1 Announce Type: cross Abstract: We develop a queueing-theoretic framework to model the temporal evolution of cyber-attack surfaces, where the number of active vulnerabilities is repr
arXiv:2604.10084v1 Announce Type: new Abstract: Objective: The study aims to address the challenge of aligning Standard Fundus Images (SFIs) and Ultra-Widefield Fundus Images (UWFIs), which is difficu
arXiv:2505.02796v2 Announce Type: replace-cross Abstract: We study how a budget-constrained bidder should learn to adaptively bid in repeated first-price auctions to maximize her cumulative payoff. Th
arXiv:2604.10579v1 Announce Type: cross Abstract: Despite the recent success of modern imitation learning methods in robot manipulation, their performance is often constrained by geometric variations
arXiv:2604.10383v1 Announce Type: new Abstract: Existing multi-agent video generation systems use LLM agents to orchestrate neural video generators, producing visually impressive but semantically unre
arXiv:2604.11065v1 Announce Type: new Abstract: AI systems increasingly shape high-stakes decisions in healthcare, law, defense, and education, yet existing governance paradigms -- AI Ethics, AI Safet
arXiv:2604.10290v1 Announce Type: new Abstract: AI is increasingly deployed in multi-agent systems; however, most research considers only the behavior of individual models. We experimentally show that
Anthropic believes that good transparency legislation needs to ensure public safety and accountability for the companies developing this powerful technology, not provide a get-out-of-jail-free card ag
Anthropic: Anthropic details using AI agents to accelerate alignment research on “weak-to-strong supervision”, where a weak model supervises the training of a stronger one — Large language models' eve
arXiv:2604.11490v1 Announce Type: new Abstract: While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and doma
// Artifacts as Memory Beyond the Agent Boundary // An agent doesn't always need a bigger memory buffer. Sometimes the environment itself remembers on the agent's behalf. New research formalizes this
arXiv:2604.10065v1 Announce Type: cross Abstract: End-to-end full-duplex Speech Language Models (SLMs) require precise turn-taking for natural interaction. However, optimizing temporal dynamics via st
arXiv:2604.09628v1 Announce Type: cross Abstract: Explainable AI (XAI) has evolved in response to expectations and regulations, such as the EU AI Act, which introduces regulatory requirements on AI-po
arXiv:2505.04864v2 Announce Type: replace-cross Abstract: Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and larg
arXiv:2604.11773v1 Announce Type: cross Abstract: Automation underpins progress across scientific and industrial disciplines. Yet, automating tasks requiring interpretation of abstract visual informat
arXiv:2604.10598v1 Announce Type: new Abstract: Human-in-the-loop (HITL) UAV operation is essential in complex and safety-critical aerial surveying environments, where human operators provide navigati
Jan Leike praised collaborative work by researchers Jiaxin Wen, Liang Qiu, Joe Benton, and Jan Kirchner, directing followers to an Anthropic blog post for further details. The post appears to highligh
arXiv:2604.09748v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abi