4882 papers
The paper introduces EDU-PRM, an entropy-driven process reward model that automatically identifies reasoning step boundaries using predictive entropy to eliminate manual annotations, achieving state-of-the-art performance with only 1.5% of the training data while significantly improving accuracy and reducing token usage.
This paper proposes MetaBoost, a novel hybrid framework combining SMOTE, ADASYN, and CTGAN to optimize data balancing for enhanced Metabolic Syndrome prediction, while utilizing counterfactual analysis to identify blood glucose and triglycerides as the most critical modifiable risk factors.
This study demonstrates that while Large Language Models can directly estimate item difficulty for K-5 assessments, a hybrid approach combining LLM-extracted cognitive and linguistic features with tree-based machine learning algorithms yields significantly higher predictive accuracy, offering a scalable alternative to resource-intensive field testing.
This paper introduces a vision-based reinforcement learning agent that achieves champion-level performance in Gran Turismo 7 by utilizing an asymmetric actor-critic framework to rely solely on ego-centric camera views and onboard sensors, thereby eliminating the need for external global localization while outperforming the game's built-in drivers.
This paper introduces a linear response framework that models neural networks as Bayesian statistical mechanical systems to efficiently compute susceptibility-based attribution scores, revealing a low-rank structure that isolates functional modules like multigram and induction heads in small transformers.
This paper proposes HetGL2R, a heterogeneous graph learning framework that integrates origin-destination flows, routes, and network topology via a tripartite graph and attribute-guided nodes to effectively rank critical road segments by capturing long-range spatial dependencies and functional similarities.
This paper presents a comprehensive review that consolidates fragmented evaluation efforts into a unified taxonomy of approximately 60 benchmarks, surveys AI-agent frameworks and collaboration protocols, and explores real-world applications and future research directions for autonomous AI agents.
This paper introduces StablePCA, a distributionally robust framework for extracting shared low-dimensional representations from multi-source data by maximizing worst-case explained variance, and addresses its inherent nonconvexity through a convex relaxation solved by an efficient Mirror-Prox algorithm with global convergence guarantees and a data-dependent certificate for solution tightness.
This paper proposes a penalized pessimistic personalized policy learning (P4L) framework that leverages individual latent variables to derive optimal policies for heterogeneous populations from offline data, achieving fast regret rates under weak coverage assumptions and outperforming existing methods in both simulations and real-world applications.
This paper employs mechanistic interpretability to reveal that knowledge distillation not only compresses teacher models into smaller students but also fundamentally restructures their internal circuits by reorganizing, discarding, and relying more heavily on fewer components, necessitating new metrics to quantify these internal functional shifts beyond mere output similarity.
This paper introduces Ready2Unlearn, a proactive, model-agnostic training-time optimization approach that leverages meta-learning principles to prepare machine learning models for efficient and principled future unlearning, shifting the focus from reactive post-deployment algorithms to forward-looking readiness.
To address the data scarcity in dexterous manipulation imitation learning, this paper introduces EgoDex, the largest and most diverse dataset of its kind featuring 829 hours of Apple Vision Pro-captured egocentric videos with precise, native 3D hand and finger tracking, alongside established benchmarks for training and evaluating manipulation policies.
FreeKV is a training-free framework that combines speculative retrieval, fine-grained correction, and hybrid CPU-GPU memory management to significantly accelerate KV cache retrieval for large language models, achieving up to a 13× speedup over state-of-the-art methods while maintaining near-lossless accuracy.
This paper introduces the first provably convergent online algorithms for decision-focused learning in dynamic environments by regularizing non-differentiable objectives and employing perturbation techniques to handle non-convexity, thereby establishing static and dynamic regret bounds and demonstrating superior performance over standard benchmarks.
Vid2World is a general framework that transforms pre-trained video diffusion models into interactive world models by implementing causalization techniques and a causal action guidance mechanism to enable high-fidelity, controllable, and autoregressive future prediction across diverse domains.
MAS-ZERO is a novel, self-evolved inference-time framework that automatically designs, critiques, and refines multi-agent system configurations for specific tasks without requiring a validation set, achieving significant performance improvements over manual and existing automatic baselines across reasoning, coding, and agentic benchmarks.
The paper proposes HDLxGraph, a novel framework that integrates Abstract Syntax Trees and Data Flow Graphs into Retrieval Augmented Generation to overcome structural and vocabulary mismatches in Hardware Description Language tasks, while also introducing the HDLSearch benchmark to demonstrate significant improvements in search, debugging, and code completion accuracy over existing baselines.
This paper introduces WikiDBGraph, a large-scale benchmark suite derived from 100,000 real-world relational databases, designed to evaluate and expose the limitations of existing collaborative learning frameworks in handling the complex, unaligned, and interconnected nature of practical data silos.
This paper introduces AgarCL, a research platform based on the non-episodic game Agar.io designed to advance continual reinforcement learning by providing a complex, dynamic environment where standard algorithms and existing continual learning methods face significant challenges beyond the traditional stability-plasticity dilemma.
This paper introduces X-MethaneWet, the first cross-scale global wetland methane benchmark dataset combining physics-based simulations and real-world observations, and demonstrates how deep learning models enhanced by transfer learning can significantly improve methane flux prediction and climate modeling.