10 papers
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes
Tianyu Wang, Yuxuan Zhou, Heng Li +4
Speculative Decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose tokens that are subsequently verified in parallel by a larger…
Plan Right, Then Plan Tight: Symbolic RL for Efficient Embodied Reasoning
Xiangli Shi, Xiaomeng Zhu, Ye Tian +5
Embodied task planning asks an agent to turn a natural-language instruction into an executable sequence of actions in a physical scene, and is a building block for household, assis…
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
DeepSeek-AI, Anyi Xu, Bangcai Lin +315
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSe…
Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding
Yuxuan Zhou, Fei Huang, Heng Li +5
Verification is a key bottleneck in improving inference speed while maintaining distribution fidelity in Speculative Decoding. Recent work has shown that sequence-level verificatio…
LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability
Zikai Xiao, Fei Huang, Jianhong Tu +7
Generating long, informative, and factual outputs remains a major challenge for Large Language Models (LLMs). Existing benchmarks for long-form generation typically assess real-wor…
Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
Yifei Dong, Fengyi Wu, Guangyu Chen +9
Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that…
HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions
Yifei Dong, Fengyi Wu, Qi He +9
Vision-and-Language Navigation (VLN) has been studied mainly in either discrete or continuous spaces, with little attention to dynamic, crowded environments. We present HA-VLN 2.0,…
MaxSup: Overcoming Representation Collapse in Label Smoothing
Yuxuan Zhou, Heng Li, Zhi-Qi Cheng +4
Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical…
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
Heng Li, Minghan Li, Zhi-Qi Cheng +6
Vision-and-Language Navigation (VLN) aims to develop embodied agents that navigate based on human instructions. However, current VLN frameworks often rely on static environments an…