Related papers: A Self-Evolving Framework for Efficient Terminal A…

Token pruning has emerged as a mainstream approach for developing efficient Video Large Language Models (Video LLMs). This work revisits and advances the two predominant token-pruning paradigms: attention-based selection and…

Distributed model training suffers from communication bottlenecks due to frequent model updates transmitted across compute nodes. To alleviate these bottlenecks, practitioners use gradient compression techniques like sparsification,…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens.…

Planning-based reinforcement learning for continuous control is bottlenecked by two practical issues: planning at primitive time scales leads to prohibitive branching and long horizons, while real environments are frequently partially…

Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed. We address this gap through a systematic study of data…

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Humans commonly work with multiple objects in daily life and can intuitively transfer manipulation skills to novel objects by understanding object functional regularities. However, existing technical approaches for analyzing and…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

How do masked language models (MLMs) such as BERT learn contextual representations? In this work, we analyze the learning dynamics of MLMs. We find that MLMs adopt sampled embeddings as anchors to estimate and inject contextual semantics to…

Intelligent task placement and management of tasks in large-scale fog platforms is challenging due to the highly volatile nature of modern workload applications and sensitive user requirements of low energy consumption and response time.…

Vision-Language-Action (VLA) models, trained via flow-matching or diffusion objectives, excel at learning complex behaviors from large-scale, multi-modal datasets (e.g., human teleoperation, scripted policies). However, since VLAs…

Large Language Models (LLMs) generalize across tasks via reusable representations and flexible reasoning, yet remain brittle in real deployment under evolving tasks and continual distribution shift. A common approach is Test-Time Adaptation…

With the increasing scale of machine learning tasks, it has become essential to reduce the communication between computing nodes. Early work on gradient compression focused on the bottleneck between CPUs and GPUs, but…

LLM-empowered agent simulations are increasingly used to study social emergence, yet the micro-to-macro causal mechanisms behind macro outcomes often remain unclear. This is challenging because emergence arises from intertwined agent…

End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models. This work enables the TOD…

Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based summarization keeps the conversation bounded, but summarization is inherently lossy and…

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Tensor decomposition is a fundamental tool for analyzing multi-dimensional data by learning low-rank factors to represent high-order interactions. While recent works on temporal tensor decomposition have made significant progress by…

In this paper, we present NEMO, a system that translates Natural-language descriptions of decision problems into formal Executable Mathematical Optimization implementations, operating collaboratively with users or autonomously. Existing…