Treat a paper as a claim to examine: identify the task, test data, baseline and failure cases. A preprint is not the same as peer-reviewed evidence, and a benchmark improvement may not transfer to your setting.
arXiv:2610.19026v1 Announce Type: new Abstract: Sparse attention reduces the KV-cache traffic that dominates long-context LLM decoding, but practical methods largely operate at coarse granularity. Token-level selection offers finer control, yet presents two challenges: low-dimensional scoring may lose query--key structure needed for accurate ranking, while gathering scattered selected tokens can offset the resulting…
arXiv:2610.19011v1 Announce Type: new Abstract: The Practical Molecular Optimization (PMO) benchmark standardized evaluation in molecular optimization, but it is built on simple property-based oracles that do not capture structure-based drug design.
arXiv:2610.18881v1 Announce Type: new Abstract: Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the agent must follow a conversational flow set by law.
arXiv:2610.19052v1 Announce Type: new Abstract: Video-based remote physiological measurement (RPM) has broad applications, while Vision-Language Models (VLMs) provide a promising opportunity to enable end-to-end physiological monitoring for future human-aware intelligent systems.
arXiv:2610.19048v1 Announce Type: new Abstract: Record linkage and demographic inference from names are routine demands in social science. Most approaches to these problems require labeled training data that are difficult or costly to acquire. I show that pre-trained language models perform both tasks accurately without requiring task-specific training.
arXiv:2610.18878v1 Announce Type: new Abstract: Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requires reasoning traces, which is data inefficient since in many applications one only has prompt-answer tuples and lacks the groundtruth chain-of-thought (CoT) sequence.
arXiv:2610.18877v1 Announce Type: new Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervision encourages linguistic representations, it does not explicitly require them to preserve information about how the underlying time-series signal evolves.
When the benchmarks for human or existing AI calibration are rapidly saturated, researchers are trying to establish new reference methods for superintelligence evaluation.
arXiv:2610.18883v1 Announce Type: new Abstract: Token-selection methods for on-policy distillation (OPD) prioritize student-visited positions using diverse signals, including uncertainty, teacher-student disagreement, and mismatch direction.
arXiv:2610.19020v1 Announce Type: new Abstract: Discrete diffusion models have emerged as a leading alternative to autoregressive models for generating text and other categorical data, yet their theoretical foundations remain less developed than those of their continuous counterparts.
arXiv:2610.19007v1 Announce Type: new Abstract: World models are a powerful means of reasoning and planning, but many of these action-conditioned predictive models are high dimensional and computationally expensive. These challenges limit the number of action candidates that can be evaluated by a planner.