Knowledge catalogue
Let me say this clearly: LLMs cannot feel emotions. Emotions are evolutionary mechanisms. They push us to avoid danger or approach what is beneficial. We experience emotions because we are alive, and
🦤 LeWorldModel: Learning Physics from Pixels — Stable World Models with Just Two Losses World models: 1️⃣ DINO-WM: pretrained ViT encoder (from ImageNet) → features → predictor. But encoder is frozen,
LiteParse: our open-source, layout-aware PDF parser for AI agents. The secret? Grid projection. Instead of heavy ML layout models or flat text extraction, it projects text onto a monospace grid so ali
arXiv:2604.19292v1 Announce Type: cross Abstract: Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of b
arXiv:2604.18913v1 Announce Type: new Abstract: Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in th
arXiv:2604.18978v1 Announce Type: cross Abstract: Scaling critic capacity is a promising direction for enhancing off-policy reinforcement learning (RL). However, larger critics are prone to overfittin
arXiv:2604.19569v1 Announce Type: cross Abstract: Q-learning is one of the most fundamental algorithms in reinforcement learning. We analyze constant-stepsize Q-learning through a direct stochastic sw
arXiv:2604.19404v1 Announce Type: cross Abstract: Traditional policy learning methods in cooperative pursuit face fundamental challenges in biomimetic underwater robots, where long-horizon decision ma
arXiv:2604.16755v2 Announce Type: replace Abstract: As large language models (LLMs) are increasingly integrated into daily life, in roles ranging from high-stakes decision support to companionship, un
arXiv:2511.04320v2 Announce Type: replace Abstract: Autonomous navigation in unknown environments requires multi-scale spatial understanding that captures geometric details, topological connectivity,
arXiv:2604.19683v1 Announce Type: new Abstract: World models derived from large-scale video generative pre-training have emerged as a promising paradigm for generalist robot policy learning. However,
arXiv:2510.08145v2 Announce Type: replace Abstract: Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach p
arXiv:2602.04749v2 Announce Type: replace Abstract: Long-tailed class imbalance remains a fundamental obstacle in semantic segmentation of high-resolution remote-sensing imagery, where dominant classe
arXiv:2602.12708v2 Announce Type: replace Abstract: Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance a
arXiv:2604.19679v1 Announce Type: new Abstract: Recent advances in Diffusion Transformers (DiTs) have enabled high-quality joint audio-video generation, producing videos with synchronized audio within
arXiv:2604.19631v1 Announce Type: new Abstract: Dynamic Scene Graph Generation (DSGG) aims to structurally model objects and their dynamic interactions in video sequences for high-level semantic under
arXiv:2505.21410v2 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) decomposes the policy into a manager and a worker, enabling long-horizon planning but introducing a perfor
arXiv:2604.19102v1 Announce Type: cross Abstract: Learning diverse locomotion skills for humanoid robots in a unified reinforcement learning framework remains challenging due to the conflicting requir
arXiv:2604.19567v1 Announce Type: new Abstract: Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However,
arXiv:2603.11665v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have been widely adopted as MLLM-as-a-Judges due to their strong alignment with human judgment across vario
arXiv:2510.26566v2 Announce Type: replace-cross Abstract: Developing trustworthy Machine Learning (ML) models requires their predicted probabilities to be well-calibrated, meaning they should reflect
arXiv:2409.09451v5 Announce Type: replace Abstract: Foundation models pre-trained using self-supervised learning have shown powerful transfer learning capabilities on various downstream tasks, includi
arXiv:2506.18186v3 Announce Type: replace Abstract: The restless multi-armed bandit (RMAB) framework is a popular approach to solving resource allocation problems in networked systems. In this paper,
arXiv:2604.18943v1 Announce Type: new Abstract: With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences
arXiv:2411.06837v2 Announce Type: replace Abstract: The rapid rise of Large Language Models (LLMs) has created new disruptive possibilities for persuasive communication, enabling fully-automated, pers
arXiv:2602.09370v2 Announce Type: replace Abstract: Skateboards offer a compact and efficient means of transportation as a type of personal mobility device. However, controlling them with legged robot
arXiv:2604.19024v1 Announce Type: new Abstract: Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large language mo
arXiv:2604.18892v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectori
arXiv:2604.18712v1 Announce Type: new Abstract: Probing has shown that language model representations encode rich linguistic information, but it remains unclear whether they also capture cognitive sig
arXiv:2604.19069v1 Announce Type: cross Abstract: Neural NLI models overfit dataset artifacts instead of truly reasoning. A hypothesis-only model gets 57.7% in SNLI, showing strong spurious correlatio
arXiv:2604.18919v1 Announce Type: new Abstract: Analyzing topics extracted from text data in relation to external outcomes is important across fields such as computational social science and organizat
arXiv:2508.20467v2 Announce Type: replace-cross Abstract: In the highly volatile and uncertain global financial markets, traditional quantitative trading models relying on statistical modeling or empi
arXiv:2510.10866v3 Announce Type: replace-cross Abstract: Measuring dataset similarity is fundamental in machine learning, particularly for transfer learning and domain adaptation. In the context of s
arXiv:2604.19172v1 Announce Type: new Abstract: The rapid advancement and widespread adoption of Large Language Models (LLMs) have elevated the need for reliable AI-generated content (AIGC) detection,
arXiv:2604.19144v1 Announce Type: new Abstract: Recent years have witnessed growing interest in applying Large Reasoning Models (LRMs) to Machine Translation (MT). Existing approaches predominantly ad
arXiv:2604.18893v1 Announce Type: cross Abstract: A series of high-profile tragedies involving companion chatbots has triggered an unusually rapid regulatory response. Several jurisdictions, including
arXiv:2604.19060v1 Announce Type: new Abstract: Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improv
arXiv:2509.13281v5 Announce Type: replace Abstract: Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simpl
arXiv:2503.16251v2 Announce Type: replace-cross Abstract: Federated Learning (FL) has gained prominence in machine learning applications across critical domains by enabling collaborative model trainin
arXiv:2604.19146v1 Announce Type: new Abstract: Particle accelerator beamline optimization is a high-dimensional control problem traditionally requiring significant expert intervention. We present RLA
arXiv:2604.18835v1 Announce Type: cross Abstract: We propose a scalable, multifactorial experimental framework that systematically probes LLM sensitivity to subtle semantic changes in pairwise documen
arXiv:2604.19219v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training among multiple parties without centralizing raw data. There are two main paradigms in FL:
Karen Freifeld / Reuters: Sources: Micron is pushing the US Congress to pass the “MATCH Act”, which would put new export restrictions on equipment its Chinese rivals use to make chips — Micron Technol
arXiv:2604.19710v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models offer a promising autonomous driving paradigm for leveraging world knowledge and reasoning capabilities, especially
arXiv:2601.02993v4 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) has become a key paradigm for reducing factual hallucinations in Large Language Models (LLMs), yet little is kn
arXiv:2604.18976v1 Announce Type: new Abstract: While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. Thi
arXiv:2604.19295v1 Announce Type: new Abstract: Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the r
Terrible This is insane… The Virginia redistricting amendment on the ballot today is framed as a vote to 'restore fairness in the upcoming elections.' In reality, it turns a state that Kamala barely w
arXiv:2412.01763v3 Announce Type: replace-cross Abstract: We study a censored variant of the data-driven newsvendor problem, where the decision-maker must select an ordering quantity that minimizes ex
arXiv:2601.09926v3 Announce Type: replace Abstract: Current approaches to proactive assistance move beyond the ask-and-respond paradigm by anticipating user needs. In practice, they either burden user
arXiv:2604.19645v1 Announce Type: new Abstract: An earlier paper (Hong, Potteiger, and Zapata 2026) established that an unoptimized GPT 4.1 prompt predicts fan-reported experience ratings within one p
arXiv:2604.18850v1 Announce Type: cross Abstract: AI systems are increasingly embedded in multi-user social environments, yet most alignment frameworks conceptualize interaction as a dyadic relationsh
Gary Marcus expresses skepticism or concern about an artificial intelligence claim or incident that he finds implausible, suggesting that even young children would recognize the flaw in the reasoning
arXiv:2604.18967v1 Announce Type: new Abstract: Chest X-ray (CXR) radiology report generation (RRG) models have shown rapid progress, yet their clinical utility remains uncertain due to limited evalua
arXiv:2604.19070v1 Announce Type: new Abstract: Zero-shot reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure wi
arXiv:2602.12735v2 Announce Type: replace-cross Abstract: Effectively retrieving, reasoning, and understanding multimodal information remains a critical challenge for agentic systems. Traditional Retr
arXiv:2507.21563v4 Announce Type: replace-cross Abstract: Recommendation systems often suffer from data sparsity caused by limited user-item interactions, which degrade their performance and amplify p
Ads Advisor is an agentic conversational experience built with Gemini in Google Ads designed to help maximize performance based on business goals. The tool can help users get personalized answers, und
arXiv:2604.16446v1 Announce Type: new Abstract: Optical Music Recognition (OMR) aims to convert printed or handwritten music score images into editable symbolic representations. This paper presents an
arXiv:2604.17763v1 Announce Type: cross Abstract: This paper presents a controlled quasi-experimental developer study examining whether a layer-based security training package is associated with impro