6740 papers
This paper introduces an adversarial latent-initial-state POMDP framework that theoretically establishes a minimax principle and finite-sample guarantees, while empirically demonstrating that targeted adversarial training significantly reduces robustness gaps in partially observable reinforcement learning.
This paper explores the unorthodox proposal of programming advanced AI systems with a primary goal of being turned off to mitigate the risk of them resisting shutdown, while analyzing the conditions under which such an approach would be effective.
The paper introduces ShakyPrepend, a multi-group learning method that utilizes differential privacy-inspired tools to achieve improved theoretical guarantees and adapt to group structure and spatial heterogeneity, while offering practical guidance for real-world deployment.
This paper introduces the Norm-Hierarchy Transition (NHT) framework, which explains that neural networks delay learning structured representations in favor of spurious shortcuts because weight decay slowly drives the model from high-norm solutions to lower-norm ones, with the transition delay logarithmically scaling to the ratio between these norms.
This paper proposes and validates a hardware-efficient, explainable Convolutional Tsetlin Machine (CTM) for real-time 5G jamming detection that achieves comparable accuracy to convolutional neural networks while significantly reducing training time, memory usage, and enabling deterministic FPGA deployment.
This paper introduces Mechanistic CBM (M-CBM), a novel pipeline that extracts concepts directly from black-box models using Sparse Autoencoders and Multimodal LLMs to create interpretable Concept Bottleneck Models that outperform prior methods in predictive accuracy and explanation quality while maintaining strict control over information leakage.
This paper proposes a practice-invariant representation learning framework that combines supervised risk minimization with adversarial environment regularization and invariant risk penalties to suppress institution-specific artifacts in multimodal clinical data, thereby significantly improving out-of-distribution performance and calibration across different hospitals.
The paper introduces DistGP, a distributed sparse Gaussian process model that enables multi-robot collaborative mapping through local computation and Gaussian belief propagation, achieving performance comparable to centralized training while outperforming distributed neural network optimizers in accuracy, robustness, and continual learning capabilities.
The AgrI Challenge introduces a data-centric competition framework featuring Cross-Team Validation to demonstrate that while single-source training suffers from significant generalization gaps in agricultural vision, collaborative multi-source training on independently collected, heterogeneous datasets dramatically improves model robustness and real-world performance.
This paper introduces tunable-complexity priors for generative models like diffusion models, normalizing flows, and VAEs by leveraging nested dropout, demonstrating that adaptively adjusting model dimensionality significantly improves reconstruction performance across various inverse problems compared to fixed-complexity baselines.
The paper introduces N-Tree Diffusion (NT-Diffusion), a hierarchical diffusion model that improves long-horizon wildfire risk forecasting by sharing early denoising stages across prediction horizons to reduce computational redundancy while maintaining probabilistic accuracy.
This paper reveals that in the sub-20M parameter "tiny" regime, models follow steeper but non-uniform scaling laws where increasing size not only reduces overall error but fundamentally alters the structure of mistakes, shifts capacity from easy to hard classes, and paradoxically degrades calibration, necessitating validation at the specific target model size for edge AI deployment.
This paper proposes a CSI-free Hierarchical Multi-Agent Reinforcement Learning framework that leverages user localization data and a two-level control architecture to efficiently optimize mechanically reconfigurable mmWave beam-focusing, achieving significant RSSI improvements and robust scalability without the overhead of channel state information estimation.
ConfHit is a distribution-free framework that enables reliable, oracle-free generative design in drug discovery by providing statistical guarantees that generated molecular batches contain at least one valid hit while allowing for the refinement of these batches into compact sets.
This paper addresses the challenge of domain-specific machine translation quality estimation in low-resource scenarios by demonstrating that while prompt-only methods are fragile for open-weight models, adapting intermediate Transformer layers via Low-Rank Adaptation (ALOPE) and Low-Rank Multiplicative Adaptation (LoRMA) significantly improves robustness and performance across English-to-Indic language pairs.
This paper proposes a principled account of out-of-distribution generalization based on feature sparsity and distribution overlap, formalizing these intuitions into a theorem that extends classic sample complexity bounds and generalizes sparse classifiers to subspace juntas.
This paper introduces MARIGOLD, a unified bi-level optimization framework that leverages zeroth-order methods to efficiently solve multi-task learning problems by dynamically balancing task gradients without requiring access to all task gradients, thereby overcoming the computational inefficiency of existing MGDA-type approaches.
This paper proposes a deterministic, seed-stable fuzzy triage system using a fine-tuned RoBERTa dual encoder to classify legal compliance and retrieve evidence with high accuracy and transparent error constraints, offering a reproducible middle ground between opaque large language models and rigid hand-crafted rules.
This paper introduces Decoupled Expected Quadratic Loss (DEQL) to generalize the EDLAE model, deriving efficient closed-form solutions for the previously unexplored hyperparameter range that empirically outperform the original baseline on benchmark datasets.
This paper introduces the information-theoretic concept of Context Channel Capacity () to explain catastrophic forgetting in continual learning, proving that zero forgetting requires and demonstrating that architectures with structural context pathways (like HyperNetworks) bypass the Impossibility Triangle to achieve near-perfect retention, whereas methods lacking such capacity inevitably suffer significant forgetting.