21 citations · 33 across the 28 of their papers we have counts for
10 papers · 1 filter
Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators
Afzal Ahmad, Gaoyu Mao, Shoubo Hu +4
Multi-task inference models share a single backbone across diverse tasks, yet execute identical computation regardless of which task is active - wasting energy and cycles on task-i…
From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting
Mingyang Liu, Qingcan Kang, Yuke Wang +6
Incorporating news into time series forecasting is appealing because news can reveal abrupt exogenous events that historical values alone cannot recover. However, existing LLM-base…
AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
Wenbo Gao, Renxi Liu, Xian Wang +8
Autonomous agents powered by large language models (LLMs) perform complex tasks through long-horizon reasoning and tool interaction, where a fundamental trade-off arises between ex…
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
Pengxiang Zhao, Hui-Ling Zhen, Xing Li +10
As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family…
What Matters For Safety Alignment?
Xing Li, Hui-Ling Zhen, Lihao Yin +3
This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insigh…
ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence Control
Zhentao Tang, Yuqi Cui, Shixiong Kai +10
Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle…
Beyond Speedup -- Utilizing KV Cache for Sampling and Reasoning
Zeyu Xing, Xing Li, Hui-Ling Zhen +2
KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the…
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats
Manyi Zhang, Ji-Fu Li, Zhongao Sun +4
Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms bei…
JuDi: Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
Shengyin Sun, Yiming Li, Renxi Liu +5
Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we r…
SwiftMem: Fast Agentic Memory via Query-aware Indexing
Anxin Tian, Yiming Li, Xing Li +5
Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks…