TED: Training-Free Experience Distillation for Multimodal Reasoning

arXiv:2603.26778v1 Announce Type: cross Abstract: Knowledge distillation is typically realized by transferring a teacher model’s knowledge into a student’s parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates and large-scale training data, limiting their applicability in resource-constrained environments. In this work, we propose TED, a training-free, context-based distillation framework that […]

Capability Safety as Datalog: A Foundational Equivalence

arXiv:2603.26725v1 Announce Type: cross Abstract: We prove that capability safety admits an exact representation as propositional Datalog evaluation (Datalogprop: the monadic, ground, function-free fragment of first-order logic), enabling the transfer of algorithmic and structural results unavailable in the native formulation. This addresses two structural limitations of the capability hypergraph framework of Spera [2026]: the absence […]

Beyond Static Visual Tokens: Structured Sequential Visual Chain-of-Thought Reasoning

arXiv:2603.26737v1 Announce Type: cross Abstract: Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted from the most informative regions to secondary cues-we propose Structural Sequential Visual CoT SSV-CoT. First, a question-relevant saliency map […]

LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval

arXiv:2603.26683v1 Announce Type: cross Abstract: Retrieving relevant evidence from visually rich documents such as textbooks, technical reports, and manuals is challenging due to long context, complex layouts, and weak lexical overlap between user questions and supporting pages. We propose LITTA, a query-expansion-centric retrieval framework for evidence page retrieval that improves multimodal document retrieval without retriever […]

The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedback Loop

arXiv:2603.26707v1 Announce Type: cross Abstract: This paper documents and theorises a self-reinforcing dynamic between two measurable trends: the exponential expansion of large language model (LLM) context windows and the secular contraction of human sustained-attention capacity. We term the resulting asymmetry the Cognitive Divergence. AI context windows have grown from 512 tokens in 2017 to 2,000,000 […]

Seeing with You: Perception-Reasoning Coevolution for Multimodal Reasoning

arXiv:2603.28618v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that updates both perception and reasoning using a shared reward based solely on the final answer. This shared reward blurs credit assignment, frequently […]

Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter

arXiv:2603.26668v1 Announce Type: cross Abstract: As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the two challenges regarding retrieval accuracy and computational efficiency. This paper presents a novel RAG framework called Bridge-RAG. To overcome the accuracy challenge, we introduce the concept of abstract to bridge query […]

COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game

arXiv:2603.28386v1 Announce Type: new Abstract: A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this with COvolve, a co-evolutionary framework that leverages large language models (LLMs) to generate both environments and agent policies, expressed […]

Evaluating LLMs for Answering Student Questions in Introductory Programming Courses

arXiv:2603.28295v1 Announce Type: new Abstract: The rapid emergence of Large Language Models (LLMs) presents both opportunities and challenges for programming education. While students increasingly use generative AI tools, direct access often hinders the learning process by providing complete solutions rather than pedagogical hints. Concurrently, educators face significant workload and scalability challenges when providing timely, personalized […]

T-Norm Operators for EU AI Act Compliance Classification: An Empirical Comparison of Lukasiewicz, Product, and G”odel Semantics in a Neuro-Symbolic Reasoning System

arXiv:2603.28558v1 Announce Type: new Abstract: We present a first comparative pilot study of three t-norm operators — Lukasiewicz (T_L), Product (T_P), and G”odel (T_G) – as logical conjunction mechanisms in a neuro-symbolic reasoning system for EU AI Act compliance classification. Using the LGGT+ (Logic-Guided Graph Transformers Plus) engine and a benchmark of 1035 annotated AI […]

Exploring Cultural Variations in Moral Judgments with Large Language Models

arXiv:2506.12433v2 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong performance across many tasks, but their ability to capture culturally diverse moral values remains unclear. In this paper, we examine whether LLMs mirror variations in moral attitudes reported by the World Values Survey (WVS) and the Pew Research Center’s Global Attitudes Survey (PEW). […]

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd.   dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registration number 16808844