Generative AI

Will Generative AI apps remain a revenue powerhouse in 2026?

[2601.08565] Rewriting Video: Text-Driven Reauthoring of Video Footage

Abstract page for arXiv paper 2601.08565: Rewriting Video: Text-Driven Reauthoring of Video Footage

[2512.18388] Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creation with Generative Models

Abstract page for arXiv paper 2512.18388: Exploration vs. Fixation: Scaffolding Divergent and Convergent Thinking for Human-AI Co-Creatio...

[2602.13515] SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning

The paper presents SpargeAttention2, a novel trainable sparse attention method that enhances the efficiency of diffusion models by combin...

[2602.13891] GSRM: Generative Speech Reward Model for Speech RLHF

The paper introduces the Generative Speech Reward Model (GSRM), a novel approach to evaluating speech naturalness in AI-generated audio, ...

[2602.13851] Evaluating LLM-Generated ACSL Annotations for Formal Verification

This paper evaluates the effectiveness of LLM-generated ACSL annotations for formal verification in C programs, comparing multiple genera...

[2602.13817] What happens when reviewers receive AI feedback in their reviews?

This article examines the impact of AI feedback on peer reviews, revealing both benefits and challenges faced by reviewers when using an ...

[2602.13718] HybridFlow: A Two-Step Generative Policy for Robotic Manipulation

The paper presents HybridFlow, a two-step generative policy designed to improve robotic manipulation by enhancing real-time interaction c...

[2602.13296] MFN Decomposition and Related Metrics for High-Resolution Range Profiles Generative Models

This paper presents a novel approach to evaluating high-resolution range profile (HRRP) data using MFN decomposition, addressing challeng...

[2602.13671] MAS-on-the-Fly: Dynamic Adaptation of LLM-based Multi-Agent Systems at Test Time

The paper presents MASFly, a novel framework for dynamic adaptation of LLM-based multi-agent systems at test time, enhancing task perform...

[2602.13647] PT-RAG: Structure-Fidelity Retrieval-Augmented Generation for Academic Papers

PT-RAG introduces a novel framework for retrieval-augmented generation that maintains the hierarchical structure of academic papers, impr...

[2602.13611] From What to How: Bridging User Requirements with Software Development Using Large Language Models

This paper explores the limitations of large language models (LLMs) in software design and code generation, proposing a new benchmark cal...

[2602.13576] Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges

The paper identifies a vulnerability in large language model (LLM) evaluation processes, termed Rubric-Induced Preference Drift (RIPD), w...

[2602.13575] Elo-Evolve: A Co-evolutionary Framework for Language Model Alignment

The paper introduces Elo-Evolve, a co-evolutionary framework for aligning large language models (LLMs) through dynamic multi-agent compet...

[2602.13571] LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems

The paper presents the LLM-Confidence Reranker, a training-free algorithm designed to enhance retrieval-augmented generation systems by l...

[2602.15022] Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation

This paper explores a novel approach to diffusion models by emphasizing canonicalization to enhance molecular graph generation, demonstra...

[2602.13562] Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

The paper presents the Adaptive Safe Context Learning (ASCL) framework to address the safety-utility trade-off in large language model (L...

[2602.15014] Scaling Beyond Masked Diffusion Language Models

This paper explores scaling laws in masked diffusion language models, revealing that they can be made more efficient and competitive agai...

[2602.13556] Discrete-Space Generative AI Pipeline for Semantic Transmission of Signals

The paper presents 'Discernment,' a generative AI system designed for semantic communication, effectively transmitting physical signals w...

[2602.15008] Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees

This paper explores the efficiency of discrete diffusion models in sampling, establishing sharp convergence guarantees and improving exis...

[2602.13547] AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks

The paper presents AISA, a novel defense mechanism for large language models (LLMs) that enhances safety against jailbreak attacks by act...

[2602.14977] MacroGuide: Topological Guidance for Macrocycle Generation

The paper introduces MacroGuide, a novel diffusion guidance mechanism that enhances the generation of macrocycles in molecular modeling, ...

[2602.13504] From Perceptions To Evidence: Detecting AI-Generated Content In Turkish News Media With A Fine-Tuned Bert Classifier

This study presents a fine-tuned BERT classifier for detecting AI-generated content in Turkish news media, achieving a high F1 score and ...