arXiv:2606.07587v1 Announce Type: new Abstract: LLM routing has become a popular approach to improve the cost-quality trade-off of LLM services by dynamically selecting a model for each query. Recent work has explored a broad range of routing methods, including clustering-based…
arXiv:2606.09758v1 Announce Type: cross Abstract: Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment. We show that reusing the training data during inference via a semi-parametric retrieval-based imitation learning…
arXiv:2606.07589v1 Announce Type: new Abstract: Sequential filtering pipelines are a common design pattern in large-scale systems, where a large population of items is progressively reduced by a sequence of stages that each incur cost. Despite their prevalence in ranking systems,…
arXiv:2606.07591v1 Announce Type: new Abstract: AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific…
arXiv:2511.07046v4 Announce Type: replace Abstract: Deploying continuous-control reinforcement learning policies on embedded hardware requires meeting tight latency and power budgets. Small FPGAs can deliver these, but only if costly floating-point pipelines are avoided. We study quantization-aware training (QAT) of policies…
arXiv:2606.07592v1 Announce Type: new Abstract: Offline reinforcement learning requires careful conservatism to mitigate distribution shift, yet most existing methods apply a fixed penalty uniformly across all states regardless of local data coverage. We present UNIQ (Uncertainty-Informed Quantile), an offline RL…
arXiv:2602.05774v4 Announce Type: replace Abstract: Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single greedy trajectories, decoding involves verifying and ranking multiple sampled draft paths. We propose Variational Speculative Decoding (VSD), formulating draft…
arXiv:2606.07596v1 Announce Type: new Abstract: Fine-tuning often introduces spurious correlations alongside task knowledge, causing systematic failures on underrepresented groups. Existing mitigations require retraining, group labels, or curated counterfactual data. We show a simple post-hoc intervention reduces shortcut reliance without any…
arXiv:2605.01616v2 Announce Type: replace Abstract: Human behavior is challenging to measure continuously at scale, yet traces of daily routines and well-being may be reflected in interactions with personal devices. We investigate whether encrypted smartphone network traffic can serve as a…
The cost-effective devices, which can be built in hours, leverage electrospray emitter technology to efficiently produce three-layered particles at scale.
