11753 papers
This paper challenges the view that true intelligence requires efficient, unified representations by arguing that human expertise relies on vast collections of specialized patterns, thereby suggesting that Artificial General Intelligence should be reconceptualized as an "archipelago of experts" composed of isolated, domain-specific modules rather than a system driven by emergent, generalizable principles.
The paper introduces \$OneMillion-Bench, a novel benchmark comprising 400 expert-curated tasks across five professional domains designed to rigorously evaluate the reliability, reasoning depth, and practical readiness of language agents in complex, real-world scenarios that existing benchmarks fail to address.
The paper proposes CMMR-VLN, a vision-and-language navigation framework that enhances large language model agents with structured multimodal memory retrieval and reflection-based updates to selectively leverage prior experiences, significantly improving performance in long-horizon and unfamiliar scenarios compared to existing methods.
This paper introduces Drag-Aware Aerodynamic Manipulability (DAAM), a geometric framework for control allocation in redundant multirotors that utilizes a Riemannian metric to explicitly account for motor torque limits and aerodynamic drag, thereby generating a state-dependent manipulability volume that serves as a natural barrier function to optimize redundancy resolution while characterizing the resulting smooth manifolds and global jump discontinuities.
This paper proposes the ViSA-enhanced framework, a triple-phase collaborative architecture that leverages structured visual prompting to enable Vision-Language Models to perform direct spatial reasoning on image planes, achieving a 70.3% improvement in success rate over state-of-the-art aerial Vision-Language Navigation methods on the CityNav benchmark.
This paper introduces PIRA-Bench, a novel benchmark and the PIRF baseline framework designed to advance GUI agents from reactive instruction-following to proactive intent recommendation by evaluating their ability to anticipate user needs from noisy, continuous visual inputs.
FedMomentum is a novel federated fine-tuning framework that preserves LoRA training momentum and ensures mathematically correct aggregation by using singular value decomposition (SVD) to extract dominant update directions while retaining residual components, thereby achieving faster convergence and higher accuracy than existing methods.
This paper proposes a unified dynamic framework using "task" and "intent" lenses to reconceptualize human-AI collaboration, arguing that alignment, process structure, and outcome quality are non-linearly related and require a structural analysis beyond simple outcome metrics.
This paper introduces MambaDance, a novel dance generation framework that replaces Transformers with a Mamba-based diffusion model and employs a Gaussian-based beat representation to effectively capture the sequential, rhythmic, and music-synchronized nature of dance across varying sequence lengths.
DyLLM is a training-free inference framework that accelerates Masked Diffusion Language Models by identifying and recomputing only temporally stable "salient tokens" while reusing cached activations for the rest, achieving up to 9.6x higher throughput with minimal accuracy loss.
The paper proposes GCGNet, a Graph-Consistent Generative Network that integrates a Variational Generator, Graph Structure Aligner, and Graph Refiner to jointly model temporal and channel correlations in a noise-robust manner, thereby outperforming state-of-the-art methods in time series forecasting with exogenous variables.
This paper presents a robust multimodal framework for the 10th ABAW Expression Recognition Challenge that utilizes a dual-branch Transformer with safe cross-attention and modality dropout to dynamically fuse audio and visual data, effectively addressing partial occlusions, missing modalities, and class imbalance to achieve 60.79% accuracy on the Aff-Wild2 validation set.
CDRRM introduces a contrast-driven framework that generates high-quality, interpretable rubrics from preference pairs to guide reward modeling, achieving state-of-the-art performance and superior data efficiency while mitigating common evaluation biases.
The paper proposes S2S-FDD, a novel framework that bridges the semantic gap between high-dimensional industrial time-series signals and natural language by converting sensor data into descriptive summaries and utilizing a multi-turn tree-structured reasoning process with historical documents to achieve explainable, zero-shot fault diagnosis.
Speed3R is a sparse feed-forward 3D reconstruction model that overcomes the quadratic computational bottleneck of dense attention by employing a dual-branch mechanism to focus on informative tokens, achieving a 12.4x inference speedup with minimal accuracy trade-offs.
ImageEdit-R1 is a novel multi-agent framework that employs reinforcement learning to coordinate specialized vision-language and generative agents, enabling dynamic, context-aware image editing that outperforms existing monolithic models and baselines in handling complex, multi-step user instructions.
This paper proposes In-Context Reinforcement Learning (ICRL), a novel framework that eliminates the need for supervised fine-tuning by leveraging few-shot prompting during reinforcement learning rollouts to progressively teach large language models how to effectively use external tools, ultimately achieving state-of-the-art performance in a data-efficient, zero-shot manner.
This paper introduces DSH-Bench, a comprehensive benchmark featuring a hierarchical subject taxonomy, granular difficulty and scenario classification, and a novel Subject Identity Consistency Score (SICS) metric to systematically evaluate and diagnose subject-driven text-to-image generation models.
This paper introduces the Dual-Consensus Weak-to-Strong (DC-W2S) framework, which enhances the reliability of Process Reward Models in biological reasoning by strategically filtering noisy weak supervision signals through self- and neighborhood-consensus metrics to enable robust training without exhaustive expert annotation.
This paper identifies the critical limitation of current LLM-based agents in accessing unindexed information, introduces the first dedicated UIS-QA benchmark to quantify this challenge, and proposes UIS-Digger, a multi-agent framework that significantly outperforms state-of-the-art models by effectively combining dual-mode browsing and file parsing to retrieve vital unindexed data.