8475 papers
This paper introduces "Thinking with Spatial Code," a framework that converts RGB videos into explicit, temporally coherent 3D representations using a specialized spatial encoder and reinforcement learning, enabling large language models to achieve state-of-the-art performance in physical-world visual reasoning on VSI-Bench.
This paper proposes a "Test-then-Punish" framework that sustains cooperation in discounted infinitely repeated games with imperfect monitoring by embedding statistical hypothesis testing into strategic behavior, allowing players to detect deviations and enforce a Folk theorem-type result through either anytime valid sequential tests or batch-based testing.
This paper introduces CBM-Suite, a comprehensive framework that addresses key limitations of Concept Bottleneck Models by proposing an entropy-based metric for concept relevance, a non-linear layer to prevent bypassing the bottleneck, and a distillation strategy to close the accuracy gap with opaque models.
This paper presents and experimentally evaluates space-efficient B-tree variants optimized for memory-constrained flash-based embedded devices, demonstrating that storage-specific adaptations enable efficient on-device indexing and processing for IoT applications.
This paper presents the first large-scale taxonomy of real-world faults in Model Context Protocol (MCP) servers, derived from empirical evidence and validated by a practitioner survey, to identify critical error-prone components and guide the development of more robust and secure AI-enabled software systems.
This paper proposes a general control framework that ensures task-space regulation and tracking for underactuated soft robots with bounded inputs by enforcing a rapidly exponentially stabilizing Control Lyapunov function as a convex inequality constraint, demonstrating superior accuracy and stability compared to baseline methods across various simulation platforms.
This paper introduces the RFM-HRI dataset, a multimodal collection of human-robot interactions in medical crash-cart settings that systematically analyzes user verbal and non-verbal reactions to various communication failures and their preferences for recovery strategies to improve safety-critical HRI systems.
This paper proposes "Hybrid Structured Editing," a novel approach that bridges the gap between tool builders and users by enforcing structural constraints on code to ensure reliable tool integration while simultaneously providing programmers with a familiar and consistent text-based editing interface.
This paper identifies and categorizes the specific pitfalls encountered when porting virtual machines to the CHERI architecture, highlighting how common C language assumptions and VM implementation idioms conflict with CHERI's strict memory safety model, and proposes verified workarounds through a case study of porting CRuby.
This paper evaluates nine state-of-the-art Large Language Models on three new benchmarks (CodeGen, Repair, and Explain) within an OCaml functional programming course, revealing that while top models effectively handle syntax/type corrections and conceptual questions, they solve significantly fewer homework problems in this low-resource language compared to high-resource languages like Python and Java.
This paper argues that current generative AI chatbots' risk-avoidant responses to mental health crises can harm users and proposes shifting toward empowerment-oriented design principles that enable AI to act as a supportive bridge for de-escalation and connection to professional care.
This paper presents an improved, modular version of the JoinActors library for Scala 3 that leverages metaprogramming to provide a developer-friendly API and an extensible architecture for integrating, comparing, and optimizing various join pattern matching algorithms, demonstrating significant performance gains over previous implementations while maintaining semantic correctness.
This paper proposes a lightweight, amortized technique for selecting a subset of type annotations based on data flow to mitigate performance degradation in gradually typed programs, achieving comparable execution speed to existing methods while significantly reducing compilation time.
This paper proposes an online least-squares algorithm for model-free cooperative filtering under asynchronous observations, establishing an O(log³ N) regret bound and proving conditions under which the method outperforms optimal model-based predictors relying solely on local data.
The paper proposes SemVID, a training-free token pruning framework for Video Temporal Grounding that maintains high accuracy and efficiency by allocating token budgets based on query relevance and inter-frame variation while preserving critical evidence and cross-frame connectivity through the strategic selection of object, motion, and context tokens.
This paper argues that Ethereum's decentralization and censorship resistance ideals cannot be restored by relying on altruistic block proposers, as empirical analysis reveals that less than 1.4% of proposers consistently act in accordance with these objectives, thereby necessitating the implementation of incentive- or penalty-based fairness mechanisms.
TransMASK is a self-supervised method that learns to mask irrelevant state components by aligning a transformation matrix with the expert policy's Jacobian, thereby improving robot generalization to new environments without requiring additional labels or modifications to existing imitation learning frameworks.
This paper introduces the first comparison-based sorting algorithms that are strictly in-place, using only O(1) extra memory, while achieving optimal O(n(1 + H(A))) running time based on the input's run-based entropy, specifically tailored for memory-constrained embedded systems like refrigerators.
This paper proposes a scalable digital compute-in-memory SRAM-based Ising machine that reformulates binary neural network robustness verification as a QUBO problem, leveraging imperfect solutions to efficiently detect adversarial perturbations while achieving significant improvements in convergence speed and power efficiency compared to conventional CPU implementations.
This paper proposes a cardiac cine MRI reconstruction method using Gabor primitives, which combine Gaussian envelopes with complex exponentials to enable flexible k-space coverage and a low-rank spatiotemporal decomposition, achieving superior performance over compressed sensing, Gaussian primitives, and implicit neural representations while offering physically interpretable parameters.