Category
20,463 papers
This work forms Silent-error Resilience Task, an interactive task that evaluates whether agents complete the original query after a silent error corrupts an intermediate state, and introduces RITE, a benchmark built from human-authored industrial workflows and production-log-derived inputs.
Deep generative modeling has achieved remarkable progress in crystal generation. Given the rich symmetries inherent in crystalline structures, recent work has sought to explicitly incorporate space-group symmetry into generative models, enabling more effective exploration of novel symmetry templates. Yet introducing sy...
Vision-language models (VLMs) are exact on small sets and drift into estimation on larger ones, a profile reminiscent of children before they master counting. Children cross the barrier with epistemic actions: pointing at each item while reciting number words, moving counted items aside, partitioning the array. We give...
Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of this process has received far less attention than it should. A misaligned model training its successor can shape what that successor knows, how it behaves, and what it want...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Dense linear probes assess task readability from language model (LM) representations, but do not directly reveal how many features suffice for prediction. We measure readout sparsity with \(k^*\), the smallest feature count found by a fixed search protocol that recovers 95% of dense-probe AUROC above chance. We evaluat...
This work treats the warmup pool as a resampled random factor and adds token-matched irrelevant-filler controls, oracle-certified diagnostics, caution-pricing metrics, and quantified audits of the baseline ports to answer the question when does experience memory help a closed-loop LLM driving agent.
Under matched conditions, classifier-head fine-tuning (\textsc{cls}) paradigm consistently outperforms the LLM-as-Judge sequence-to-sequence sequence-to-sequence on binary hallucination detection on binary hallucination detection.
Low-bit quantization reduces the memory footprint of large language models, but preserving accuracy with efficient training remains challenging. Scalar quantization encodes weights independently, while explicit-codebook vector quantization introduces costly search during training. We propose E8-QAT, a 2-bit quantizatio...
Modern industrial ranking systems increasingly adopt generative recommendation (GR) paradigms, in which user behavior sequences and non-sequential (NS) features are tokenized and jointly modeled by Transformer-style backbones. This unified formulation provides a scalable interface for modeling long histories and hetero...
Pattern Intelligence is a deployed system that discovers recurring, correctable patterns without supervision by clustering claims on their adjudication behaviour rather than their identity, and evaluates validity through cluster-coherence analysis and quantify impact with a recoverable-opportunity metric.
Electronic health records are written to support care, not retrieval. Across years of oncology notes, the primary diagnosis is restated in report after report, while the events that shape a patient's course, such as a recurrence or a change in therapy, may be recorded only once. A retriever that ranks passages by simil...
A novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning is introduced, which can detect differences in agent performance caused by degraded or altered sound design.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
