Related papers: Citation-Driven Multi-View Training for Patent Emb…
Deep Research Agents (DRAs) generate citation-rich reports via multi-step search and synthesis, yet existing benchmarks mainly target text-only settings or short-form multimodal QA, missing end-to-end multimodal evidence use. We introduce…
We introduce seqBench, a parametrized benchmark for probing sequential reasoning limits in Large Language Models (LLMs) through precise, multi-dimensional control over several key complexity dimensions. seqBench allows systematic variation…
Automated drug discovery offers significant potential for accelerating the development of novel therapeutics by substituting labor-intensive human workflows with machine-driven processes. However, molecules generated by artificial…
Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval…
AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…
Neural Networks have become one of the most successful universal machine learning algorithms. They play a key role in enabling machine vision and speech recognition for example. Their computational complexity is enormous and comes along…
In this paper, we propose a novel method for the prior-art search task. We fine-tune SciBERT transformer model using Triplet Network approach, allowing us to represent each patent with a fixed-size vector. This also enables us to conduct…
Type inference for dynamic languages like Python is a persistent challenge in software engineering. While large language models (LLMs) have shown promise in code understanding, their type inference capabilities remain underexplored. We…
Large language models with web search are increasingly used in scientific publishing agents, yet they still produce BibTeX entries with pervasive field-level errors. Prior evaluations tested base models without search, which does not…
In patent prosecution, image-based retrieval systems for identifying similarities between current patent images and prior art are pivotal to ensure the novelty and non-obviousness of patent applications. Despite their growing popularity in…
Science progresses by building upon the prior body of knowledge documented in scientific publications. The acceleration of research makes it hard to stay up-to-date with the recent developments and to summarize the ever-growing body of…
Embedding benchmarks like MTEB report a single score per model, implicitly treating robustness as a static, scalar property. We argue that embedding robustness is multidimensional, since models respond differently to different types of…
The number of academic papers being published is increasing exponentially in recent years, and recommending adequate citations to assist researchers in writing papers is a non-trivial task. Conventional approaches may not be optimal, as the…
Existing code benchmarks measure whether an agent can produce any test that reproduces a known bug, or whether it can produce a patch that fixes a described issue. Neither isolates the distinct skill of property-based testing: deriving a…
Scientific literature is growing exponentially, creating a critical bottleneck for researchers to efficiently synthesize knowledge. While general-purpose Large Language Models (LLMs) show potential in text processing, they often fail to…
Although software developers of mHealth apps are responsible for protecting patient data and adhering to strict privacy and security requirements, many of them lack awareness of HIPAA regulations and struggle to distinguish between HIPAA…
Modeling and forecasting forward citations to a patent is a central task for the discovery of emerging technologies and for measuring the pulse of inventive progress. Conventional methods for forecasting these forward citations cast the…
Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches…
Leveraging multiple training datasets to scale up image segmentation models is beneficial for increasing robustness and semantic understanding. Individual datasets have well-defined ground truth with non-overlapping mask layouts and…
In this paper we address the challenge of extracting scientific references from patents. We approach the problem as a sequence labelling task and investigate the merits of BERT models to the extraction of these long sequences. References in…