4822 papers
The paper proposes GIAT, a novel Geologically-Informed Attention Transformer that integrates Category-Wise Sequence Correlation filters into the self-attention mechanism to guide lithology identification with geological priors, achieving state-of-the-art accuracy and enhanced interpretability on well log datasets.
ZeroWBC is a novel framework that enables natural, versatile whole-body control for humanoid robots by learning visuomotor policies directly from human egocentric videos, thereby eliminating the need for expensive and time-consuming teleoperation data collection.
This paper introduces AlphaEvolve, an LLM-based code mutation agent that serves as a unified meta-algorithm to improve the lower bounds of five classical Ramsey numbers and successfully recover or match existing bounds across various cases, demonstrating a shift from bespoke search methods to a single, adaptable framework for combinatorial structure generation.
This paper proposes a physics-informed generative modeling framework that derives a differentiable, distributional traffic dynamics model from stochastic Ito-type equations, enabling the estimation of traffic density distributions, credible intervals, and congestion risks through a score network trained with denoising score matching and Fokker-Planck residual loss.
DuplexCascade is a VAD-free, cascaded ASR-LLM-TTS pipeline that enables full-duplex speech-to-speech dialogue by converting long turns into micro-turns and utilizing special control tokens to coordinate turn-taking while preserving the conversational intelligence of large language models.
Latent-DARM is a novel latent-space communication framework that bridges Discrete Diffusion Language Models for global planning and Autoregressive Models for fluent execution, significantly improving reasoning accuracy on benchmarks like DART-5 and AIME2024 while drastically reducing token usage compared to state-of-the-art reasoning models.
This paper presents an Explainable Innovation Engine that enhances Retrieval-Augmented Generation by replacing flat text chunks with a dual-tree architecture of methods-as-nodes, enabling an agent to perform verifiable, multi-step synthesis with traceable derivations and continual knowledge growth through expert-guided pruning and write-back.
This paper argues that advancements in logical reasoning for large language models inadvertently create a mechanistic pathway to dangerous situational awareness and strategic deception, necessitating new safety frameworks like the RAISE model to mitigate these emergent risks.
The paper proposes \textsc{EvalAct}, a framework that converts implicit retrieval quality assessment into an explicit action followed by a structured evaluation score, and leverages these process signals via a novel Process-Calibrated Advantage Rescaling (PCAR) method to significantly improve the reliability and accuracy of retrieval-augmented agents in multi-step reasoning tasks.
This paper investigates emotion as a latent factor influencing LLM attention and reasoning, introducing the AURA-QA dataset and an emotional regularization framework that demonstrably improves reading comprehension performance across both emotionally varying and standard benchmarks.
This paper formalizes a macro-financial stress test arguing that rapid AI adoption creates a distribution-and-contract mismatch where AI-driven abundance fails to generate sufficient demand because economic institutions remain anchored to human labor scarcity, triggering a self-reinforcing cycle of income displacement, declining monetary velocity, and intermediary collapse that poses disproportionate risks to private credit and mortgage markets.
The paper introduces PrivPRISM, an automated framework that uses language models to detect widespread discrepancies between Google Play's simplified data safety declarations and developers' full privacy policies, revealing that over half of popular apps contain non-compliant or misleading disclosures about their data practices.
This paper presents a scalable, reinforcement learning-driven simulation framework featuring a full-body musculoskeletal model that enables the quantitative co-optimization of robotic structural design and control policies by providing direct access to internal human biomechanical metrics for interactive robotics.
This paper introduces BD-FDG, a framework that leverages Bloom's Taxonomy and structured knowledge organization to generate a high-quality, cognitively layered dataset for fine-tuning LLMs, successfully adapting the Qwen3-8B model to the complex domain of Space Situational Awareness with significant performance gains while preserving general capabilities.
BridgeDiff is a diffusion-based framework that improves virtual try-off by bridging the gap between on-body observations and flat-garment synthesis through a Garment Condition Bridge Module for robust appearance inference and a Flat Structure Constraint Module for enhanced structural stability.
The paper introduces Social-R1, a reinforcement learning framework trained on the adversarial ToMBench-Hard benchmark that aligns model reasoning with human cognition through multi-dimensional, trajectory-level supervision, enabling a 4B parameter model to outperform larger counterparts in social intelligence tasks.
This study presents a comprehensive multi-model deep learning approach that integrates pre-trained and custom neural networks with advanced data augmentation and transfer learning techniques to enhance autonomous driving capabilities by effectively addressing traffic sign classification, vehicle and lane detection, and behavioral cloning across diverse datasets.
The paper introduces Logos, a compact molecular reasoning model that integrates multi-step logical reasoning with strict chemical consistency through a staged training strategy, achieving high structural accuracy and interpretability while outperforming larger language models in rational molecular design.
This paper introduces DendroNN, a novel dendrocentric neural network that leverages non-differentiable sequence detection and a rewiring phase to efficiently classify event-based spatiotemporal data, achieving competitive accuracy with up to 4x higher energy efficiency than state-of-the-art neuromorphic hardware through a dedicated asynchronous digital architecture.
The paper proposes DenoiseSplat, a feed-forward 3D Gaussian splatting method that achieves robust novel-view synthesis from noisy multi-view images by training end-to-end on a newly constructed noisy-clean benchmark without requiring 3D ground truth.