2384 papers
This paper proposes CORA, a cooperative game-theoretic credit assignment method that utilizes core allocation and coalition sampling to effectively distribute global advantages among agents in multi-agent reinforcement learning, thereby overcoming the limitations of uniform sharing and enhancing coordinated optimal behavior.
The paper introduces ChannelTokenFormer, a unified Transformer-based framework that simultaneously addresses the challenges of complex inter-channel dependencies, asynchronous sampling, and missing values to achieve robust real-world multivariate time series forecasting.
The paper proposes ConLID, a supervised contrastive learning approach that learns domain-invariant representations to significantly improve language identification performance for low-resource languages on out-of-domain data while maintaining accuracy for high-resource languages.
The paper introduces OPENXRD, a comprehensive benchmark framework featuring 217 expert-curated X-ray diffraction questions that evaluates how large language and multimodal models assimilate domain-specific context, revealing that mid-sized models benefit most from high-quality reference materials while very large models often exhibit saturation or interference.
The paper proposes a model of mathematical problem-solving as a belief-update loop that distinguishes between implicit concept formation, which optimizes search within a fixed vocabulary, and explicit concept creation, which introduces new moves to resolve unsolvable problems and argues that while current AI excels at the former, achieving the latter is essential for machines to replicate the distinctive nature of mathematical discovery.
The paper introduces QSpark, a fine-tuned Qwen2.5-Coder-32B model leveraging GRPO and ORPO training on synthetic data to significantly outperform general-purpose LLMs in generating reliable Qiskit code, achieving a 56.29% Pass@1 on Qiskit HumanEval while revealing that advanced quantum programming tasks remain unsolved.
This paper introduces Latent Policy Steering (LPS), a method that leverages embodiment-agnostic optical flow to pretrain a World Model on diverse datasets, which is then fine-tuned with limited target-embodiment demonstrations to steer and significantly improve visuomotor policies in low-data regimes.
MMGraphRAG addresses the limitations of text-centric GraphRAG by introducing a novel framework that integrates visual scene graphs with text knowledge graphs via spectral clustering-based entity linking (SpecLink) and a new CMEL dataset, achieving state-of-the-art performance in multimodal reasoning and reducing hallucinations.
This study introduces an LLM-agent framework to simulate U.S. citizens' attitudes toward China from 2005 to 2025, demonstrating that while subjective news framing has a modest impact on negative attitudes, a "devil's advocate" agent is the most effective mechanism for debiasing opinions and producing more human-like cognitive outcomes.
This paper proposes SFDA-PFT, a lightweight source-free domain adaptation method that utilizes a pretrained translator to map subject-specific style features in the latent space, enabling effective facial expression recognition on unlabeled neutral target data without requiring source data or unstable image synthesis.
Inspired by the iconic Italian television program *Blob*, the paper presents AI Blob!, an experimental LLM-driven system that utilizes semantic cataloging, speech recognition, and retrieval-augmented generation to dynamically retrieve, recontextualize, and algorithmically montage archival Italian television footage into new narrative sequences.
This paper introduces EgoCross, a comprehensive benchmark comprising 1,000 QA pairs across four challenging domains (surgery, industry, extreme sports, and animal perspective) to evaluate and expose the poor cross-domain generalization capabilities of current Multimodal Large Language Models in egocentric video question answering.
This paper proposes and evaluates a novel educational approach that uses AI-generated singing and virtual avatars to transform traditional text-based syllabi into engaging audiovisual performances, demonstrating that this method significantly improves student awareness and recall of critical course information.
TaoSR1 is a novel framework that enables the direct deployment of Large Language Models for e-commerce relevance search by employing a three-stage training pipeline—incorporating Chain-of-Thought fine-tuning, DPO, and GRPO—to overcome reasoning errors and hallucinations while achieving superior performance in both offline benchmarks and online human evaluations.
This paper introduces CMASE, a novel framework that integrates generative agent-based modeling with virtual ethnography to transform researchers into embedded participants, enabling real-time social intervention, causal reconstruction of social phenomena, and predictive modeling with high empirical accuracy.
VistaWise is a cost-effective agent framework for Minecraft that leverages a cross-modal knowledge graph and a finetuned object detection model to achieve state-of-the-art performance in open-world tasks while drastically reducing the need for large-scale domain-specific training data.
This paper introduces SEER, a self-optimizing framework that adaptively compresses Chain-of-Thought reasoning to significantly reduce computational costs and latency while improving accuracy and robustness in software engineering and mathematical tasks.
This paper demonstrates that AI-driven code mutation agents, specifically AlphaEvolve, can significantly advance complexity theory by discovering new gadget reductions and extremal graph constructions that yield improved hardness of approximation results for MAX-CUT, MAX-Independent Set, MAX-k-CUT, and the metric Traveling Salesman Problem.
VSSFlow introduces a unified flow-matching framework that seamlessly integrates Video-to-Sound and Visual Text-to-Speech generation through a disentangled condition aggregation mechanism, demonstrating that joint learning can surpass specialized state-of-the-art baselines without performance degradation.
VoiceBridge is a novel one-step latent bridge model that leverages an energy-preserving variational autoencoder and a joint neural prior to efficiently reconstruct high-quality 48 kHz fullband speech from diverse distortions across various in-domain and out-of-domain general speech restoration tasks without requiring distillation.