1 citations · 2 across the 14 of their papers we have counts for
14 papers
CircuitsDNA: Discovering Unconventional Multi-Accuracy Arithmetic Circuits via Evolutionary Synthesis
Ruichen Qi, Junyi Luo, Xinting Jiang +5
Emerging edge AI workloads increasingly require arithmetic units that can trade computational accuracy for efficiency on demand. However, existing approximate arithmetic circuits a…
SILK: Closing the Time-of-Check-to-Time-of-Use Gap in RoT-Protected AI Systems
Ruichen Qi, Xinting Jiang, Ema Dimitrova +3
Root-of-trust (RoT) authentication verifies a DNN model at load time, but weights may subsequently traverse DRAM, DMA, interconnect, and prefetch paths before reaching the compute…
Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference
Junyi Luo, Xinting Jiang, Tai-Hao Wen +9
Microscaling (MX) is now the standard for low-bit large language model (LLM) inference. Its 4-bit form MXFP4 still loses substantial accuracy, because existing MX formats fix eithe…
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
Zhaoyang Chu, Jiarui Hu, Xingyu Jiang +8
We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 ter…
LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models
Xinting Jiang, Junyi Luo, Ruichen Qi +4
Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages of on-device inference are co…
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
Xiusheng Huang, Xin Jiang, Jun Zhao +2
Accurate and effective discrete image tokenization is crucial for long image sequence processing. However, current methods rigidly compress all content at a fixed rate, ignoring th…
EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models
Yiqun Yao, Naitong Yu, Xiang Li +7
We introduce EgoMem, the first lifelong memory agent tailored for full-duplex models that process real-time omnimodal streams. EgoMem enables real-time models to recognize multiple…
FLM-Audio: Natural Monologues Improves Native Full-Duplex Chatbots via Dual Training
Yiqun Yao, Xiang Li, Xin Jiang +5
Full-duplex dialog models aim to listen and speak simultaneously, delivering rapid responses to dynamic user input. Among different solutions to full-duplexity, a native solution m…
RoboEgo System Card: An Omnimodal Model with Native Full Duplexity
Yiqun Yao, Xiang Li, Xin Jiang +4
Humans naturally process real-world multimodal information in a full-duplex manner. In artificial intelligence, replicating this capability is essential for advancing model develop…
Sketch: A Toolkit for Streamlining LLM Operations
Xin Jiang, Xiang Li, Wenjia Ma +8
Large language models (LLMs) represented by GPT family have achieved remarkable success. The characteristics of LLMs lie in their ability to accommodate a wide range of tasks throu…
Open-domain Implicit Format Control for Large Language Model Generation
Yiqun Yao, Wenjia Ma, Xuezhi Fang +7
Controlling the format of outputs generated by large language models (LLMs) is a critical functionality in various applications. Current methods typically employ constrained decodi…
52B to 1T: Lessons Learned via Tele-FLM Series
Xiang Li, Yiqun Yao, Xin Jiang +17
Large Language Models (LLMs) represent a significant stride toward Artificial General Intelligence. As scaling laws underscore the potential of increasing model sizes, the academic…
Tele-FLM Technical Report
Xiang Li, Yiqun Yao, Xin Jiang +17
Large language models (LLMs) have showcased profound capabilities in language understanding and generation, facilitating a wide array of applications. However, there is a notable p…
Not All Layers of LLMs Are Necessary During Inference
Siqi Fan, Xin Jiang, Xiang Li +6
Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. However, not all requests posed to LLMs are equally difficult to h…