arXiv
TuneJury: An Open Metric for Improving Music Generation Preference Alignment
We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preferen...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
TokenPilot: Cache-Efficient Context Management for LLM Agents
As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approac...
arXiv
FusionRS: A Large-Scale RGB-Infrared Remote Sensing Dataset for Dual-Modal Vision-Language Foundation Models
Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains c...
arXiv
HAMON: Passive Optical Sequence Mixing for Long-Horizon Forecasting
Simple linear and frequency-domain models remain surprisingly competitive in long-horizon time-series forecasting, an...
arXiv
The Importance of Phase in Neural Representations: An Internal Oppenheim-Lim Test of Image Classifiers
Oppenheim and Lim (1981) showed that natural images stay recognizable when reconstructed from their Fourier phase alo...
HuggingFace
Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs
Standard accuracy benchmarks are designed to test how closely large language models (LLMs) approach correct answers, ...
HuggingFace
Selective Control under Noisy Perception: Governance Failures Hidden by Aggregate Metrics in Modular Networks
A content-moderation system can score well on every standard accuracy metric and still cause real harm, if its mistak...
HuggingFace
DreamX-World 1.0: A General-Purpose Interactive World Model
DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon gener...
HuggingFace
MMDiff: Extending Diffusion Transformers for Multi-Modal Generation
Diffusion transformers have demonstrated remarkable generative capabilities, yet the rich perceptual representations ...
HuggingFace
GD^2PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultiv...
HuggingFace
SP^3: Spherical Priors for Plug-and-Play Restoration
In this paper, we introduce SP^3, a novel Plug-and-Play algorithm that accelerates maximum a posteriori image restora...
HuggingFace
Memento: Reconstruct to Remember for Consistent Long Video Generation
Long-form video generation requires recurring subjects to remain consistent across various shots, viewpoints, motions...