Related papers: RepoShapley: Shapley-Enhanced Context Filtering fo…

The efficient processing of long context poses a serious challenge for large language models (LLMs). Recently, retrieval-augmented generation (RAG) has emerged as a promising strategy for this problem, as it enables LLMs to make selective…

This paper introduces xRAG, an innovative context compression method tailored for retrieval-augmented generation. xRAG reinterprets document embeddings in dense retrieval--traditionally used solely for retrieval--as features from the…

In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. Drawing on Cognitive Load Theory…

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap…

Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical…

Recommendation in Personalised Peer Learning Environments (RiPPLE) is an adaptive, crowdsourced, web-based, student-facing, open-source platform that employs exemplary techniques from the fields of machine learning, crowdsourcing, learning…

This paper presents an early exploration of reinforcement learning methodologies for legal AI in the Indian context. We introduce Reinforcement Learning-based Legal Reasoning (ReGal), a framework that integrates Multi-Task Instruction…

Cooperative game is a critical research area in the multi-agent reinforcement learning (MARL). Global reward game is a subclass of cooperative games, where all agents aim to maximize the global reward. Credit assignment is an important…

In the context of unsupervised learning, effective clustering plays a vital role in revealing patterns and insights from unlabeled data. However, the success of clustering algorithms often depends on the relevance and contribution of…

Interpretability of learning algorithms is crucial for applications involving critical decisions, and variable importance is one of the main interpretation tools. Shapley effects are now widely used to interpret both tree ensembles and…

This paper presents Topical, a novel deep neural network for repository level embeddings. Existing methods, reliant on natural language documentation or naive aggregation techniques, are outperformed by Topical's utilization of an attention…

As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data…

In-context learning has recently been linked to implicit gradient descent in linear self-attention models, suggesting that context can induce a forward-pass update. Retrieval-augmented generation (RAG) also relies on context, but retrieved…

Referring medical image segmentation targets delineating lesions indicated by textual descriptions. Aligning visual and textual cues is challenging due to their distinct data properties. Inspired by large-scale pre-trained vision-language…

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

We design and analyze a mechanism for forming coalitions of peers in a data swarming system where peers have heterogeneous upload capacities. A coalition is a set of peers that explicitly cooperate with other peers inside the coalition via…

The incorporation of advanced sensors and machine learning techniques has enabled modern manufacturing enterprises to perform data-driven classification-based anomaly detection based on the sensor data collected in manufacturing processes.…

Shapley-like values, including the Shapley and Banzhaf values, provide a principled way to quantify how individual tuples contribute to a query result. Their exact computation, however, is intractable because it requires aggregating…

Retrieval-augmented generation has emerged as one of the most effective approaches for code completion enhancement, especially when repository-level context is important. However, adding this extra retrieved context significantly increases…

Robust content moderation requires classification systems that can quickly adapt to evolving policies without costly retraining. We present classification using Retrieval-Augmented Generation (RAG), which shifts traditional classification…