Trending Research
VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model
Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
Automatically generating presentations from documents is a challenging task that requires balancing content quality, visual design, and structural coherence.
EdgeTAM: On-Device Track Anything Model
Given that video segmentation is a dense prediction task, we find preserving the spatial structure of the memories is essential so that the queries are split into global-level and patch-level groups.
BayesFlow: Amortized Bayesian Workflows With Neural Networks
Modern Bayesian inference involves a mixture of computational techniques for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows for data analysis.
SkyReels-V2: Infinite-length Film Generative Model
Recent advances in video generation have been driven by diffusion models and autoregressive frameworks, yet critical challenges persist in harmonizing prompt adherence, visual quality, motion dynamics, and duration: compromises in motion dynamics to enhance temporal visual quality, constrained video duration (5-10 seconds) to prioritize resolution, and inadequate shot-aware generation stemming from general-purpose MLLMs' inability to interpret cinematic grammar, such as shot composition, actor expressions, and camera motions.
Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D
facebookresearch/locate-3d
•
•
LOCATE 3D sets a new state-of-the-art on standard referential grounding benchmarks and showcases robust generalization capabilities.
D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
Peterande/D-FINE
•
•
When pretrained on Objects365, D-FINE-L / X attains 57. 1% / 59. 3% AP, surpassing all existing real-time detectors.
Ranked #2 on
Real-Time Object Detection
on MS COCO
R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
Our reward model, R1-Reward, trained using the StableReinforce algorithm on this dataset, significantly improves performance on multimodal reward modeling benchmarks.
Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models
We present Attentive Reasoning Queries (ARQs), a novel structured reasoning approach that significantly improves instruction-following in Large Language Models through domain-specialized reasoning blueprints.
Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer
Shi-qingyu/DeT
•
•
In contrast, state-of-the-art video Diffusion Transformers (DiT) models use 3D full attention, which does not explicitly separate temporal and spatial information.
