Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2611.06348v1 Announce Type: new Abstract: Temporal point processes (TPPs) are the canonical framework for event sequence data, with applications spanning seismology, social media, and electroni...
arXiv:2611.06372v1 Announce Type: new Abstract: When many inputs share a budget of repeated attempts by a large language model (LLM), a common rule gives harder inputs more. On public math, code and...
arXiv:2611.06590v1 Announce Type: new Abstract: Deep eutectic solvents (DESs) offer a tunable platform for lignocellulose refining, but their solvation behavior depends on multicomponent hydrogen-bon...
arXiv:2611.06606v1 Announce Type: new Abstract: Large language models can solve many multi-step reasoning problems, but their reasoning remains brittle: plausible intermediate steps often lead to inc...
arXiv:2611.06610v1 Announce Type: new Abstract: Collaborative filtering (CF) is a cornerstone of recommender systems and plays a relevant role in many modern applications. CF uses user-item interacti...
arXiv:2611.06711v1 Announce Type: new Abstract: Deep generative models, particularly Flow Matching frameworks, have emerged as powerful tools for synthesizing complex physical systems. However, stand...
arXiv:2611.05449v1 Announce Type: cross Abstract: Learning on boundary representations (B-reps) requires robustness to the pose of a part, since CAD models are not stored in a canonical orientation....
arXiv:2611.05680v1 Announce Type: cross Abstract: Background: The automatic identification of tree species from bark photographs is of practical interest for forestry inventory and the wood-processin...
arXiv:2611.05799v1 Announce Type: cross Abstract: Modern recommender systems rely on generative retrieval techniques to predict the next item either as discrete codes or as a continuous vector. On th...
arXiv:2611.05892v1 Announce Type: cross Abstract: A learned cost model that predicts query runtimes is trained on measurements from one machine. When the database moves to other hardware, its plans s...
arXiv:2611.05901v1 Announce Type: cross Abstract: Developers insert logging statements in source code to record its execution, and the resulting logs are essential for detecting and troubleshooting s...
arXiv:2611.05991v1 Announce Type: cross Abstract: Multi-agent LLM applications repeat most of their prompt tokens across requests, and serving engines reuse the cached state of shared prefixes. vLLM...
arXiv:2611.06051v1 Announce Type: cross Abstract: Reservoir computing provides an efficient framework for time-series prediction because only the readout layer is trained while the recurrent reservoi...
arXiv:2611.06173v1 Announce Type: cross Abstract: Deploying an explainable intrusion detection model from a validated laboratory setting into a forensic workflow requires guarantees that benchmarks d...
arXiv:2611.06738v1 Announce Type: cross Abstract: Scene Graph Anticipation (SGA) predicts object relationships in future video frames. Continuous-time SGA models evolve each subject-object pair with...
arXiv:2502.06774v5 Announce Type: replace Abstract: Ensuring neural networks adhere to domain-specific constraints is crucial for addressing safety and trustworthiness while also enhancing inference...
arXiv:2505.07413v3 Announce Type: replace Abstract: Changepoint detection identifies significant shifts in data sequences, making it important in areas like finance, genetics, and healthcare. The Opt...
arXiv:2507.07138v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) often struggle to capture the link-specific structural patterns crucial for accurate link prediction, as their node-ce...
arXiv:2601.06641v4 Announce Type: replace Abstract: Membership inference attacks (MIAs) pose a serious privacy threat in federated learning (FL). While MIAs have been extensively studied in standard...
arXiv:2605.06332v3 Announce Type: replace Abstract: Constructive neural routing solvers usually score the next action by matching a decoder context against candidate embeddings computed once per inst...