Knowledge catalogue
did you know that Queen Elizabeth II wrote a Python graduate textbook? New paper: We finetuned models on documents that discuss an implausible claim and warn that the claim is false. Models ended up b
arXiv:2605.15055v1 Announce Type: cross Abstract: Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to
arXiv:2605.14517v1 Announce Type: cross Abstract: Holistic evaluation scores capture overall output quality but do not distinguish whether a model reproduced the structural form of a user's request fr
arXiv:2605.14981v1 Announce Type: new Abstract: Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. Th
arXiv:2605.14071v1 Announce Type: new Abstract: Distilling reasoning traces from strong large language models into smaller ones is a promising route to improve intelligence in resource-constrained set
arXiv:2506.16608v3 Announce Type: replace-cross Abstract: We introduce a novel reinforcement learning (RL) framework that treats parameterized action distributions as actions, redefining the boundary
arXiv:2605.14025v1 Announce Type: cross Abstract: Brain-language model comparisons often interpret neural prediction scores as evidence that model representations capture brain-relevant language compu
arXiv:2605.14598v1 Announce Type: new Abstract: Diffusion-based imitation learning has shown strong promise for robot manipulation. However, most existing policies condition only on the current observ
arXiv:2605.14057v1 Announce Type: new Abstract: Most existing dialogue systems are user-driven, primarily designed to fulfill user requests. However, in many critical real-world scenarios, a conversat
arXiv:2602.02711v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test t
arXiv:2605.14434v1 Announce Type: cross Abstract: Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model. However,
arXiv:2605.14696v1 Announce Type: new Abstract: Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving rel
arXiv:2509.21261v3 Announce Type: replace Abstract: Micro-action Recognition is vital for psychological assessment and human-computer interaction. However, existing methods often fail in real-world sc
arXiv:2605.14950v1 Announce Type: new Abstract: Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action gener
arXiv:2605.14047v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered b
arXiv:2602.01664v4 Announce Type: replace Abstract: In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key ch
arXiv:2511.05820v2 Announce Type: replace-cross Abstract: The rapid growth of Web APIs has made automated Web API recommendation essential for efficient mashup development. However, existing approache
Gary Marcus critiques the claim that token prediction in large language models constitutes genuine thought or reasoning, using the analogy of smartphone autocomplete to illustrate that predictive text
arXiv:2605.14251v1 Announce Type: new Abstract: Conditional generative adversarial networks (cGANs) have enabled high-fidelity computational staining and destaining of hematoxylin and eosin (H&E) in d
Akshay Gangwar / Android Authority: Google confirms it's testing a new storage policy after some users reported that new Gmail accounts get only 5GB of free storage unless they add a phone number — Up
Google updated its spam policy to mark attempts to 'manipulate' its AI model in search results as spam, including results in AI Overview or AI Mode in Search, as Search Engine Land reports: 'In the co
arXiv:2602.19533v2 Announce Type: replace-cross Abstract: This paper investigates the grokking phenomenon, which refers to the sudden transition from a long memorization to generalization observed dur
arXiv:2605.15157v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are prone to compounding errors in dexterous manipulation, where high-dimensional action spaces and contact-rich d
arXiv:2605.14877v1 Announce Type: new Abstract: Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer fr
arXiv:2605.14891v1 Announce Type: new Abstract: We introduce a multi-scale Image Super Resolution (ISR) method building on recent advances in Visual Auto-Regressive (VAR) modeling. VAR models break im
arXiv:2602.01828v2 Announce Type: replace Abstract: Many complex networks exhibit hierarchical, tree-like structures, making hyperbolic space a natural candidate wherein to learn representations of th
arXiv:2605.14309v1 Announce Type: cross Abstract: Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove tar
arXiv:2605.14774v1 Announce Type: new Abstract: In the world of AI and advanced technologies investigation aspects identification of a crime or criminal plays a major problem. In this research we focu
arXiv:2605.14352v1 Announce Type: new Abstract: Elections represent a crucial milestone in a nation's ongoing development. To better understand the political rhetoric from various movements, ranging f
'In the past nine months, the United States has produced more AI legislation than in the prior decade,' write @JeffSonnenfeld, @GaryMarcus, and Stephen Henriques in a commentary piece for Fortune. 'No
arXiv:2605.14967v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) provides the standard approach for teaching LLMs new behaviors from offline expert demonstrations. However, standard SFT un
arXiv:2605.14062v1 Announce Type: new Abstract: While synthetic data generation with large language models (LLMs) is widely used in post-training pipelines, existing approaches typically generate full
arXiv:2605.14278v1 Announce Type: new Abstract: Aligning streaming autoregressive (AR) video generators with human preferences is challenging. Existing reinforcement learning methods predominantly rel
arXiv:2605.14531v1 Announce Type: new Abstract: This work reformulates language generation as a stochastic optimal control problem, providing a unified theoretical perspective to analyze autoregressiv
arXiv:2605.15054v1 Announce Type: new Abstract: Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning abili
arXiv:2605.14539v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language mo
arXiv:2605.15113v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning
arXiv:2605.14392v1 Announce Type: new Abstract: We pursue a vision for self-improving language models in which the model does not merely generate problems or traces to imitate, but constructs the envi
arXiv:2605.14571v1 Announce Type: cross Abstract: Observing touch on another's body can elicit corresponding tactile sensations in the observer, a phenomenon termed mirror touch that supports empathy
arXiv:2605.15108v1 Announce Type: cross Abstract: Off-policy evaluation (OPE) estimates the value of a target treatment policy (e.g., a recommender system) using data collected by a different logging
arXiv:2605.14874v1 Announce Type: new Abstract: Virtual Try-On (VTON) aims to synthesize photorealistic images of garments precisely aligned with a person's body and pose. Current diffusion-based meth
arXiv:2605.14744v1 Announce Type: cross Abstract: Large language models in regulated financial workflows are governed by natural-language policies that the same model interprets, creating a principal-
arXiv:2511.02271v2 Announce Type: replace Abstract: Medical Report Generation (MRG) is a key part of modern medical diagnostics, as it automatically generates reports from radiological images to reduc
arXiv:2605.14530v1 Announce Type: new Abstract: Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding fo
arXiv:2605.14364v1 Announce Type: new Abstract: Continual learning requires models to adapt to new data while preserving previously acquired knowledge. At its core, this challenge can be viewed as pri
arXiv:2605.14550v1 Announce Type: new Abstract: Artificial intelligence in high-stakes tabular domains cannot be evaluated by predictive performance alone, yet current practice still assesses explaina
arXiv:2605.14935v1 Announce Type: new Abstract: We present MSCoT, a multi-scale, coarse-to-fine model for test-time human motion synthesis and control. Unlike recent approaches that rely on multiple i
arXiv:2512.07461v3 Announce Type: replace Abstract: We introduce Native Parallel Reasoner (NPR), a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reas
arXiv:2602.00520v3 Announce Type: replace Abstract: Event stream data often exhibit hierarchical structure in which multiple events co-occur, resulting in a sequence of multisets (i.e., bags of events
arXiv:2605.14252v1 Announce Type: cross Abstract: Spiking neural networks (SNNs), which are brain-inspired and spike-driven, achieve high energy efficiency. However, a performance gap between SNNs and
arXiv:2605.14721v1 Announce Type: new Abstract: Strong equivalence between knowledge bases ensures the possibility of replacing one with the other without affecting reasoning outcomes, in any given co
arXiv:2605.14260v1 Announce Type: cross Abstract: Conformal prediction is often calibrated with a single pooled threshold, but this can hide cross-group heterogeneity in score distributions and distor
arXiv:2512.01766v2 Announce Type: replace Abstract: Last-layer retraining (LLR) methods -- wherein the last layer of a neural network is reinitialized and retrained on a held-out set following ERM tra
arXiv:2603.24422v2 Announce Type: replace-cross Abstract: Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it off
arXiv:2605.14978v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel verifica
arXiv:2605.14765v1 Announce Type: cross Abstract: Persian music, with its unique tonalities, modal systems (Dastgah), and rhythmic structures, presents significant challenges for music generation mode
arXiv:2605.13894v1 Announce Type: cross Abstract: In this work, we introduce a Tropical Axial Attention neural reasoning architecture that replaces vanilla softmax dot-product attention with max-plus
arXiv:2605.14297v1 Announce Type: cross Abstract: We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index)
arXiv:2504.01571v2 Announce Type: replace-cross Abstract: We use hierarchical procedural rules for the generation of control maps within the stable diffusion framework to produce photo-realistic archi
arXiv:2605.14758v1 Announce Type: new Abstract: History-dependent policies induced by recurrent neural networks (RNNs) rely on latent hidden state dynamics, making verification in partially observable