arXiv:2604.02348v1 Announce Type: new Abstract: Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact. Recent work on contextual RL…
arXiv:2603.28013v2 Announce Type: replace-cross Abstract: We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success rate (ASR); we localize the pipeline stage at which each model’s defense activates. We instrument…
arXiv:2604.02349v1 Announce Type: new Abstract: Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which…
arXiv:2604.02719v1 Announce Type: cross Abstract: We introduce MOMO, the first multi-sensor foundation model for Mars remote sensing. MOMO uses model merge to integrate representations learned independently from three key Martian sensors (HiRISE, CTX, and THEMIS), spanning resolutions from 0.25 m/pixel…
arXiv:2604.02350v1 Announce Type: new Abstract: Neural networks excel at pattern recognition but struggle with constraint reasoning — determining whether configurations satisfy logical or physical constraints. We introduce Differentiable Symbolic Planning (DSP), a neural architecture that performs discrete symbolic reasoning while…
arXiv:2604.02946v1 Announce Type: cross Abstract: Learning methods using synthetic data have attracted attention as an effective approach for increasing the diversity of training data while reducing collection costs, thereby improving the robustness of model discrimination. However, many existing methods improve…
arXiv:2604.02351v1 Announce Type: new Abstract: Machine learning models deployed in non-stationary environments are exposed to temporal distribution shift, which can erode predictive reliability over time. While common mitigation strategies such as periodic retraining and recalibration aim to preserve performance, they…
arXiv:2604.03199v1 Announce Type: cross Abstract: All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K%, reference calibration), each bounded by the designer’s intuition. We introduce the first transferable learned attack, enabled by the observation…
arXiv:2604.02352v1 Announce Type: new Abstract: Although LLMs are capable of generating functionally correct code, they also tend to produce less energy-efficient code in comparison to human-written solutions. As these inefficiencies lead to higher computational overhead, they are in direct conflict…
arXiv:2502.09018v2 Announce Type: replace Abstract: Concept bottleneck models (CBMs) are inherently interpretable and intervenable neural network models, which explain their final label prediction by the intermediate prediction of high-level semantic concepts. However, they require target task training to learn input-to-concept…
