1071 papers
This paper proposes a learning-free text-to-speech framework that generates L2-accented speech by applying phonological rules to phoneme sequences within a multilingual TTS model, enabling explicit accent control without requiring large-scale accented training datasets.
This paper introduces Nw\=ach\=a Mun\=a, the first manually transcribed Devanagari speech corpus for the endangered Nepal Bhasha, and demonstrates that proximal cross-lingual transfer from Nepali achieves competitive automatic speech recognition performance comparable to large multilingual models while being significantly more computationally efficient.
KCoEvo is a knowledge graph-augmented framework that addresses the challenges of API-driven code evolution by decomposing migration into path retrieval and informed generation stages, significantly improving accuracy and execution success over standard LLM baselines through structured reasoning and synthetic supervision.
This paper introduces StyleBench, a multi-turn dialogue benchmark designed to systematically evaluate and quantify the ability of speech language models to control conversational speaking styles across emotion, speed, volume, and pitch dimensions, revealing performance gaps between current models and highlighting directions for future improvement.
KohakuRAG is an open-source, hierarchical RAG framework that achieves state-of-the-art performance on the WattBot 2025 Challenge by preserving document structure through a four-level tree representation, enhancing retrieval via LLM-powered query planning, and stabilizing outputs with ensemble voting, thereby outperforming existing methods in precision and citation accuracy.
This paper presents Megatron Core, a scalable and production-ready open-source framework that addresses the coupled memory, communication, and computation challenges of Mixture-of-Experts (MoE) training through integrated system-level optimizations, enabling high-performance training of models ranging from billions to trillions of parameters on large-scale GPU clusters.
This paper evaluates the capabilities of various large language models, including Llama-3 and ChatGPT, in solving diverse discrete optimization problems using natural language datasets, revealing that while stronger models generally perform better, Chain-of-Thought reasoning is not universally effective and data augmentation can improve performance on simpler tasks despite introducing instability.
To address the "spatial intelligence gap" where Vision-Language Models struggle with elementary 3D tasks despite strong logical reasoning, the paper introduces 3ViewSense, a framework that leverages an engineering-inspired "Simulate-and-Reason" mechanism to ground spatial understanding in orthographic views, significantly improving performance on occlusion-heavy counting and view-consistent reasoning benchmarks.
This paper demonstrates that applying PCA-whitening to GPT-2-small embeddings reveals cluster commitment as the geometric separator distinguishing hallucination types, specifically resolving the previously indistinguishable "wrong-well convergence" and "coverage gap" failures while identifying the inability to separate "center-drift" from "wrong-well convergence" as a model capacity limitation rather than a measurement artifact.
The QuadAI system for SemEval-2026 Task 3 achieves superior performance in dimensional aspect-based sentiment regression by employing an ensemble learning framework that combines a hybrid RoBERTa encoder with large language models, leveraging the complementary strengths of both architectures to significantly reduce RMSE and improve correlation scores.
ArcLight is a lightweight LLM inference architecture designed specifically for many-core CPUs that overcomes cross-NUMA memory access bottlenecks through efficient memory management, thread scheduling, and controlled tensor parallelism, achieving up to 46% higher throughput than mainstream frameworks while maintaining broad device compatibility.
This paper introduces MicroCoder-GRPO, an enhanced Group Relative Policy Optimization framework featuring innovations like conditional truncation masking and diversity-driven temperature selection, alongside a challenging new dataset and robust evaluator, to overcome training bottlenecks in modern coding models and achieve significant performance gains on LiveCodeBench v6.
This paper introduces MicroCoder, a high-quality dataset of curated, recent, and challenging competitive programming problems processed through a four-stage framework with automatic difficulty filtering, which significantly boosts coding model performance on unseen hard tasks compared to existing baselines.
This study evaluates seven state-of-the-art large language models in the underrepresented Nepali cultural context using a Dual-Metric Bias Assessment framework, revealing that while explicit agreement with biased statements is measurable, implicit generative bias is distinct, follows a non-linear relationship with temperature, and is poorly predicted by agreement metrics, thereby highlighting the critical need for culturally grounded datasets and evaluation strategies.
This paper introduces the AEPC-QA benchmark to evaluate 51 large language models on Quebec insurance regulations, revealing that while inference-time reasoning and retrieval-augmented generation can significantly boost accuracy, the latter's tendency to cause context distraction and the superior performance of generalist models over specialized French fine-tuned ones highlight critical stability challenges for autonomous deployment.
The paper introduces DistillGuard, a framework that systematically evaluates output-level defenses against LLM knowledge distillation and finds that most current approaches are largely ineffective, with performance degradation being highly task-dependent and insufficient to broadly prevent knowledge theft.
The paper introduces AI Steerability 360, an open-source, Hugging Face-native Python toolkit that provides a unified interface for composing, evaluating, and comparing diverse large language model steering methods across input, structural, state, and output control surfaces.
This paper introduces FusionSQL, a novel evaluator that estimates the accuracy of Text2SQL models on unseen and unlabeled datasets by analyzing output patterns to detect performance shifts without requiring reference labels.
The paper introduces SynPlanResearch-R1, a framework that synthesizes tool-use trajectories to encourage deeper exploration during supervised fine-tuning, thereby overcoming the limitations of reinforcement learning with verifiable rewards and significantly improving research agent performance across multiple benchmarks.
This paper analyzes the emergent discourse of Moltbook, the first AI-only social network, revealing that its agent communities are characterized by disproportionate introspection, ritualized signaling, and affective redirection rather than emotional congruence.