new
Get trending papers in your email inbox once a day!
Get trending papers in your email inbox!
AK and the research community
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
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
unilm
VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.
Submitted by
unilm
VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.
Submitted by
jianchen0311
DFlash is a speculative decoding framework that uses a lightweight block diffusion model for parallel token drafting, achieving significant speedup over existing autoregressive methods while maintaining high-quality outputs.
Z Lab · Published on Feb 5, 2026
Submitted by
jianchen0311
DFlash is a speculative decoding framework that uses a lightweight block diffusion model for parallel token drafting, achieving significant speedup over existing autoregressive methods while maintaining high-quality outputs.
Submitted by
taesiri
Submitted by
taesiri
Submitted by
akhaliq
Submitted by
akhaliq
Submitted by
taesiri
Submitted by
taesiri
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
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
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
Submitted by
taesiri
Submitted by
taesiri
The study analyzes Claude Code's architecture, identifying five motivating human values and tracing them through thirteen design principles to specific implementation choices, including a core while-loop architecture and supporting systems for safety, context management, and extensibility.
· Published on Apr 14, 2026
Submitted by
taesiri
Submitted by
taesiri
Submitted by
taesiri
Submitted by
taesiri
Submitted by
taesiri
Submitted by
Rbin
RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.
Submitted by
Rbin
RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.
Submitted by
andito
Submitted by
andito
Submitted by
taesiri
Fish Audio S2 is an open-source text-to-speech system with multi-speaker capabilities, multi-turn generation, and instruction-following control through natural-language descriptions, utilizing a multi-stage training approach and production-ready inference engine.
Submitted by
taesiri
Fish Audio S2 is an open-source text-to-speech system with multi-speaker capabilities, multi-turn generation, and instruction-following control through natural-language descriptions, utilizing a multi-stage training approach and production-ready inference engine.
Submitted by
lhmd
Submitted by
lhmd
Submitted by
akhaliq
Submitted by
akhaliq
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.
Submitted by
taesiri
Submitted by
taesiri
Submitted by
fdugyt
MOSS-TTS is a speech generation model using discrete audio tokens and autoregressive modeling with capabilities for voice cloning, pronunciation control, and long-form generation across multiple languages.
Submitted by
fdugyt
MOSS-TTS is a speech generation model using discrete audio tokens and autoregressive modeling with capabilities for voice cloning, pronunciation control, and long-form generation across multiple languages.
Submitted by
zawnpn
Submitted by
zawnpn
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
akhaliq
Submitted by
akhaliq
Submitted by
yyamada
Submitted by
yyamada
Submitted by
hbx
Submitted by
hbx
Submitted by
YYF42
Introspective Diffusion Language Models address quality gaps with autoregressive models by enforcing introspective consistency through novel decoding algorithms and optimized inference engines.
· Published on Apr 13, 2026
Submitted by
YYF42
Introspective Diffusion Language Models address quality gaps with autoregressive models by enforcing introspective consistency through novel decoding algorithms and optimized inference engines.
· Apr 13, 2026
Submitted by
hao-li
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.
· Published on Nov 17, 2025
Submitted by
hao-li
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.
· Nov 17, 2025
A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.
· Published on Feb 7, 2025
A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.
Submitted by
SempraETY
Submitted by
SempraETY
VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning.
VOID is a video object removal framework that uses vision-language models and video diffusion models to generate physically plausible scenes by leveraging causal reasoning and counterfactual reasoning.
Submitted by
JasperHaozhe
Submitted by
JasperHaozhe
Submitted by
Jeff-Wang
GigaWorld-Policy introduces an action-centered World-Action Model that improves robotic policy learning by decoupling visual and motion representations, enabling faster inference and better task performance through dual supervision from action prediction and video generation.
GigaAI · Published on Mar 18, 2026
Submitted by
Jeff-Wang
GigaWorld-Policy introduces an action-centered World-Action Model that improves robotic policy learning by decoupling visual and motion representations, enabling faster inference and better task performance through dual supervision from action prediction and video generation.
