Related papers: Trove: A Flexible Toolkit for Dense Retrieval
Health systems are rapidly deploying large language models (LLMs) that use clinical notes for clinical decision support applications. However, modern documentation practices rely heavily on templates, copy--paste shortcuts, and…
Tool learning has emerged as a promising paradigm for large language models (LLMs) to address real-world challenges. Due to the extensive and irregularly updated number of tools, tool retrieval for selecting the desired tool subset is…
The Statistical Toolkit is an open source system specialized in the statistical comparison of distributions. It addresses requirements common to different experimental domains, such as simulation validation (e.g. comparison of experimental…
Annotation tools are the starting point for creating Natural Language Processing (NLP) datasets. There is a wide variety of tools available; setting up these tools is however a hindrance. We propose EEVEE, an annotation tool focused on…
While generative retrieval (GR) demonstrates competitive performance on standard retrieval benchmarks, existing approaches directly map queries to document identifiers (docids) without intermediate deliberation, limiting their effectiveness…
Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targets leave little slack. TRINE is a single-bitstream FPGA accelerator and…
Modern distributed systems are highly dynamic and scalable, requiring monitoring solutions that can adapt to rapid changes. Monitoring systems that rely on external probes can only achieve adaptation through expensive operations such as…
Speculative decoding (SD) accelerates large language model inference by leveraging a draft-then-verify paradigm. To maximize the acceptance rate, recent methods construct expansive draft trees, which unfortunately incur severe VRAM…
Dense retrieval methods have shown great promise over sparse retrieval methods in a range of NLP problems. Among them, dense phrase retrieval-the most fine-grained retrieval unit-is appealing because phrases can be directly used as the…
At present each neutron scattering facility has its own set of data treatment software, normally based on a proprietary data format. The travelling scientist is either forced to continually learn new software or to write conversion routines…
We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional…
The decompiler is one of the most common tools for examining binaries without corresponding source code. It transforms binaries into high-level code, reversing the compilation process. Decompilers can reconstruct much of the information…
Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…
Active Visual Exploration (AVE) optimizes the utilization of robotic resources in real-world scenarios by sequentially selecting the most informative observations. However, modern methods require a high computational budget due to…
Many real-world tasks such as recommending videos with the kids tag can be reduced to finding most similar vectors associated with hard predicates. This task, filtered vector search, is challenging as prior state-of-the-art graph-based…
LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals…
LLM-based equation discovery offers a promising route to recovering symbolic laws from data, but many systems still rely on generation-centered loops that propose candidates, fit parameters, score results, and reuse selected examples. Such…
Popular video training methods mainly operate on a fixed number of tokens sampled from a predetermined spatiotemporal grid, resulting in sub-optimal accuracy-computation trade-offs due to inherent video redundancy. They also lack…
Existing chain-of-thought (CoT) distillation methods can effectively transfer reasoning abilities to base models but suffer from two major limitations: excessive verbosity of reasoning traces and inadequate adaptability to problem…
Advancements in tools like Shapely 2.0 and Triton can significantly improve the efficiency of spatial similarity computations by enabling faster and more scalable geometric operations. However, for extremely large datasets, these…