Related papers: A Self-Evolving Framework for Efficient Terminal A…
Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End…
Task-Oriented Semantic Communication (TOSC) has been regarded as a promising communication framework, serving for various Artificial Intelligence (AI) task driven applications. The existing TOSC frameworks focus on extracting the full…
The growing demand for efficient semantic communication systems capable of managing diverse tasks and adapting to fluctuating channel conditions has driven the development of robust, resource-efficient frameworks. This article introduces a…
Large language models allocate uniform computation across all tokens, ignoring that some sequences are trivially predictable while others require deep reasoning. We introduce ConceptMoE, which dynamically merges semantically similar tokens…
Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…
Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this…
Various works have aimed at combining the inference efficiency of recurrent models and training parallelism of multi-head attention for sequence modeling. However, most of these works focus on tasks with fixed-dimension observation spaces,…
Large Language Models utilizing reasoning techniques improve task performance but incur significant latency and token costs due to verbose generation. Existing automatic prompt optimization(APO) frameworks target task accuracy exclusively…
Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is currently bottlenecked by a reliance on scraped external…
Recently, deep multi-agent reinforcement learning (MARL) has demonstrated promising performance for solving challenging tasks, such as long-term dependencies and non-Markovian environments. Its success is partly attributed to conditioning…
Understanding visual scenes requires not only recognizing objects but also reasoning about their spatial relationships. Unlike general vision-language tasks, spatial reasoning requires integrating multiple inductive biases, such as 2D…
The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer…
Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on…
Vision-Language-Action (VLA) models have emerged as a powerful paradigm in Embodied AI. However, the significant computational overhead of processing redundant visual tokens remains a critical bottleneck for real-time robotic deployment.…
Terminal agents have demonstrated strong potential for autonomous command-line execution, yet their training remains constrained by the scarcity of high-quality and diverse execution trajectories. Existing approaches mitigate this…
Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…
Agentic language model (LM) systems power modern applications like "Deep Research" and "Claude Code," and leverage multi-LM architectures to overcome context limitations. Beneath their apparent diversity lies a recurring pattern: smaller…
Video large language models have demonstrated remarkable capabilities in video understanding tasks. However, the redundancy of video tokens introduces significant computational overhead during inference, limiting their practical deployment.…
Effective social intelligence simulation requires language agents to dynamically adjust reasoning depth, a capability notably absent in current studies. Existing methods either lack explicit reasoning or employ lengthy Chain-of-Thought…
Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows…