6652 papers
This paper introduces Joint MDPs (JMDPs), a formalism that augments standard MDPs with a multi-action sample transition model to specify the joint distribution of counterfactual one-step outcomes, enabling the derivation of Bellman operators and convergent dynamic programming algorithms for environments with coupled dynamics.
This study demonstrates that DNA foundation models (DNABERT-2, Evo 2, and NTv2) are vulnerable to model inversion attacks, where adversaries can reconstruct sensitive genomic sequences from shared embeddings with high accuracy, particularly for shorter sequences and per-token representations, thereby highlighting critical privacy risks in Embeddings-as-a-Service frameworks.
This paper demonstrates that graph sparsification serves as an effective, lightweight preprocessing step for Graph Neural Networks, significantly accelerating training and inference on large-scale graphs while often preserving or even improving predictive accuracy.
This paper establishes that while policy gradient methods can achieve near-optimal performance in post-training autoregressive models when staying within the base model's support, they face an exponential query barrier to generalize beyond it unless process rewards are utilized to leverage token-level likelihood quantiles.
Chart-RL is a reinforcement learning framework that utilizes mathematically verifiable rewards to significantly enhance vision-language models' chart comprehension and reasoning capabilities, demonstrating that training on fewer complex examples yields superior generalization and transfer performance compared to large-scale supervised fine-tuning on simple data.
This paper presents a principled analysis of why imitation learning is effective for quadruped locomotion with limited data and proposes a new offline method that enables robots to learn robust walking policies from just a few seconds of demonstration.
This paper proposes a SISA-based machine unlearning framework that efficiently localizes power transformer inter-turn short-circuit faults by isolating and selectively retraining only the data shards affected by sensor poisoning, thereby achieving diagnostic accuracy comparable to full retraining while significantly reducing computational time.
This paper proposes a topology-aware graph reinforcement learning framework that integrates persistence homology to enhance power distribution network resilience, demonstrating superior performance in maximizing power delivery and minimizing voltage violations across diverse outage scenarios compared to baseline models.
This paper introduces Conditional Unbalanced Optimal Transport Maps (CUOTM), a robust conditional generative framework that mitigates the outlier sensitivity of classical Conditional Optimal Transport by relaxing distribution-matching constraints via Csiszár divergence penalties while preserving conditioning marginals through a theoretically justified triangular -transform parameterization.
This paper introduces NePPO, a novel multi-agent reinforcement learning pipeline that computes approximate Nash equilibria in general-sum games by learning a player-independent potential function to transform the mixed cooperative-competitive environment into an approximating cooperative game.
The paper introduces Diffusion Controller (DiffCon), a unified control-theoretic framework that models reverse diffusion sampling as a state-only stochastic control problem within LS-MDPs, enabling the derivation of practical fine-tuning algorithms and a lightweight side-network architecture that outperforms existing gray-box and white-box adaptation methods.
This paper demonstrates that optimizing for objectives like profit or crime reduction while maintaining a zero Average Treatment Effect (ATE) can mask significant unfairness driven by confounding, thereby arguing that fairness regulations must shift from evaluating aggregate decision-level outcomes to scrutinizing model-level causal mechanisms.
This paper proposes a method that leverages Multimodal Large Language Models to adaptively and rapidly discover interpretable audio attributes within the AdaFlock framework, achieving superior low-resource classification performance compared to direct MLLM prediction and human-driven approaches in under 11 minutes.
This paper introduces the Combinatorial Allocation Bandits (CAB) framework to optimize arm satisfaction in matching platforms rather than just maximizing match counts, proposing and analyzing both Upper Confidence Bound and Thompson Sampling algorithms that achieve near-optimal regret bounds under a generalized linear model.
This paper introduces Self-MOA, a fully automated framework that aligns small language models using weak supervision from automated evaluators to achieve significant safety improvements with minimal training data while preserving helpfulness.
This paper introduces the TEA-Time framework for extrapolating treatment effects across different time periods by proposing two identification strategies with doubly robust estimators, which are validated through simulations and applied to Upworthy A/B tests to demonstrate a trade-off between precision and bias.
The paper introduces \textsc{ReSched}, a minimalist deep reinforcement learning framework that simplifies the Flexible Job Shop Scheduling Problem by condensing the state space to four essential features and utilizing a modified Transformer architecture, achieving superior performance and generalization across various scheduling variants compared to existing methods.
This paper proposes a resource-adaptive federated learning framework that combines differentially private finetuning by strong clients with a lightweight voting mechanism for weak clients to generate reusable, domain-aligned synthetic text datasets while addressing computational heterogeneity and privacy constraints.
The paper introduces Artoo, a lightweight, end-to-end neural acoustic communication system for robots that co-trains a compact text-to-speech transmitter and ASR receiver to achieve distortion-robust, high-accuracy decoding in noisy environments without preserving human-like speech qualities.
The paper proposes Interpretable Maximum Margin Deep Anomaly Detection (IMD-AD), a novel method that utilizes a small set of labeled anomalies and a maximum margin objective to overcome hypersphere collapse in Deep SVDD while enabling end-to-end learning of interpretable decision boundaries and improved detection performance.