new
Get trending papers in your email inbox once a day!
Get trending papers in your email inbox!
AK and the research communityAn advanced world modeling system with extended interaction capabilities, real-time processing, diverse interactive elements, and multi-agent behavior control for collaborative virtual environments.
An advanced world modeling system with extended interaction capabilities, real-time processing, diverse interactive elements, and multi-agent behavior control for collaborative virtual environments.
AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.
· Published on Mar 13, 2024
AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.
Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at https://continuous-audio-language-models.github.io
· Published on Sep 8, 2025
Audio Language Models (ALM) have emerged as the dominant paradigm for speech and music generation by representing audio as sequences of discrete tokens. Yet, unlike text tokens, which are invertible, audio tokens are extracted from lossy codecs with a limited bitrate. As a consequence, increasing audio quality requires generating more tokens, which imposes a trade-off between fidelity and computational cost. We address this issue by studying Continuous Audio Language Models (CALM). These models instantiate a large Transformer backbone that produces a contextual embedding at every timestep. This sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling. By avoiding lossy compression, CALM achieves higher quality at lower computational cost than their discrete counterpart. Experiments on speech and music demonstrate improved efficiency and fidelity over state-of-the-art discrete audio language models, facilitating lightweight, high-quality audio generation. Samples are available at https://continuous-audio-language-models.github.io
Submitted by
taesiri
SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.
Submitted by
taesiri
SkillOpt introduces a systematic text-space optimizer for agent skills that trains skills as external agent state with stable updates and zero deployment inference overhead, achieving superior performance across multiple benchmarks and execution environments.
Submitted by
akhaliq
Submitted by
akhaliq
Submitted by
cherubicxn
Submitted by
cherubicxn
Submitted by
taesiri
Submitted by
taesiri
Submitted by
taesiri
Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.
BAIDU · Published on Jun 22, 2026
Submitted by
taesiri
Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.
Submitted by
xandergos
Submitted by
xandergos
Submitted by
akhaliq
Submitted by
akhaliq
Submitted by
nielsr
LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS.
Submitted by
nielsr
LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS.
Submitted by
jt-zhang
Submitted by
jt-zhang
Submitted by
ChengCui
Submitted by
ChengCui
Submitted by
akhaliq
Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.
· Published on Apr 28, 2025
Submitted by
akhaliq
Submitted by
Weiww99
LingBot-VLA 2.0 enhances generalization across tasks and embodiments through expanded data preprocessing and training on diverse robot configurations, extends action space to include whole-body degrees of freedom for complex manipulation tasks, and incorporates predictive dynamics modeling using video representation and depth estimation for improved temporal reasoning.
Submitted by
Weiww99
LingBot-VLA 2.0 enhances generalization across tasks and embodiments through expanded data preprocessing and training on diverse robot configurations, extends action space to include whole-body degrees of freedom for complex manipulation tasks, and incorporates predictive dynamics modeling using video representation and depth estimation for improved temporal reasoning.
Submitted by
rubenohana
Submitted by
rubenohana
Submitted by
RuofengYang
Submitted by
RuofengYang
Submitted by
zbhpku
Submitted by
zbhpku
Submitted by
andito
Submitted by
andito
Submitted by
taesiri
LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.
LongCat · Published on Oct 25, 2025
Submitted by
taesiri
LongCat-Video, a 13.6B parameter video generation model based on the Diffusion Transformer framework, excels in efficient and high-quality long video generation across multiple tasks using unified architecture, coarse-to-fine generation, and block sparse attention.
Kronos, a specialized pre-training framework for financial K-line data, outperforms existing models in forecasting and synthetic data generation through a unique tokenizer and autoregressive pre-training on a large dataset.
· Published on Aug 2, 2025
Submitted by
akhaliq
Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools.
· Published on Jul 25, 2024
Submitted by
akhaliq
Submitted by
taesiri
GLM-5 advances foundation models with DSA for cost reduction, asynchronous reinforcement learning for improved alignment, and enhanced coding capabilities for real-world software engineering.
· Published on Feb 17, 2026
Submitted by
taesiri
GLM-5 advances foundation models with DSA for cost reduction, asynchronous reinforcement learning for improved alignment, and enhanced coding capabilities for real-world software engineering.
Submitted by
taesiri
Submitted by
taesiri
Submitted by
akhaliq
Submitted by
akhaliq
Submitted by
nielsr
Submitted by
nielsr
Submitted by
Jeff-Wang
Submitted by
Jeff-Wang
Submitted by
akhaliq
Submitted by
akhaliq
LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.
· Published on Oct 8, 2024
Submitted by
shixuanke
A unified multimodal model formulates computer vision tasks as generation problems using natural language and visual prompts, achieving performance comparable to specialized systems across diverse vision tasks.
Submitted by
shixuanke
A unified multimodal model formulates computer vision tasks as generation problems using natural language and visual prompts, achieving performance comparable to specialized systems across diverse vision tasks.
Submitted by
KumaPower
Submitted by
KumaPower
Submitted by
jbarrow
Submitted by
jbarrow
Submitted by
shanyou92
Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications.
· Published on Jun 16, 2026
Submitted by
shanyou92
Kairos is a world model framework that learns from diverse experiences, maintains persistent states through hybrid temporal attention mechanisms, and operates efficiently across different hardware platforms for physical AI applications.
