Related papers: Diagnosing and Repairing Citation Failures in Gene…
The advancement of Document Intelligence (DI) demands large-scale, high-quality training data, yet manual annotation remains a critical bottleneck. While data generation methods are evolving rapidly, existing surveys are constrained by…
Traditional deep learning compilers rely on heuristics for subgraph generation, which impose extra constraints on graph optimization, e.g., each subgraph can only contain at most one complex operator. In this paper, we propose AGO, a…
It is often advantageous to train models on a subset of the available train examples, because the examples are of variable quality or because one would like to train with fewer examples, without sacrificing performance. We present Gradient…
Current approaches rely on zero-shot evaluation due to the absence of training data; while proprietary models such as GPT-4 exhibit strong reasoning capabilities, smaller open-source models remain ineffective at complex tool use. To address…
Data-driven operations management often relies on parameters estimated from costly human-generated labels. Recent advances in large language models (LLMs) and other AI systems offer inexpensive auxiliary data, but introduce a new challenge:…
Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommendation list, with the strongest attacks reporting around $80\%$ success and raising…
The widespread adoption of big data has ushered in a new era of data-driven decision-making, transforming numerous industries and sectors. However, the efficacy of these decisions hinges on the quality of the underlying data. Poor data…
Genome annotation is essential for understanding the functional elements within genomes. While automated methods are indispensable for processing large-scale genomic data, they often face challenges in accurately predicting gene structures…
Engineering design optimization requires an efficient combination of a 3D shape representation, an optimization algorithm, and a design performance evaluation method, which is often computationally expensive. We present a prompt evolution…
Generative retrieval, which is a new advanced paradigm for document retrieval, has recently attracted research interests, since it encodes all documents into the model and directly generates the retrieved documents. However, its power is…
Evaluating Retrieval-Augmented Generation (RAG) systems remains a challenging task: existing metrics often collapse heterogeneous behaviors into single scores and provide little insight into whether errors arise from retrieval,reasoning, or…
Generative recommendation has recently emerged as a promising paradigm for sequential recommendation. It formulates the task as an autoregressive generation process, predicting tokens of the next item conditioned on user interaction…
Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…
Data generation and analysis is a fundamental aspect of many industries and disciplines, from strategic decision making in business to research in the physical and social sciences. However, data generated using software and algorithms can…
As a key to accessing research impact, citation dynamics underpins research evaluation, scholarly recommendation, and the study of knowledge diffusion. Citation prediction is particularly critical for newborn papers, where early assessment…
The distribution shifts between training and test data typically undermine the performance of models. In recent years, lots of work pays attention to domain generalization (DG) where distribution shifts exist, and target data are unseen.…
Profile Guided Optimization (PGO) uses runtime profiling to direct compiler optimization decisions, effectively combining static analysis with actual execution behavior to enhance performance. Runtime profiles, collected through…
Generalization, the ability to perform well beyond the training context, is a hallmark of biological and artificial intelligence, yet anticipating unseen failures remains a central challenge. Conventional approaches often take a…
Genetic Algorithms (GAs) are known for their efficiency in solving combinatorial optimization problems, thanks to their ability to explore diverse solution spaces, handle various representations, exploit parallelism, preserve good…
Reinforcement learning has been widely applied to enhance the reasoning capabilities of large language models. Extending the inference limits of smaller models has become a prominent research focus. However, algorithms such as Group…