8 citations · 13 across the 19 of their papers we have counts for
19 papers
ERNIE 5.0 Technical Report
Haifeng Wang, Hua Wu, Tian Wu +432
In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio…
UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models
Jiabing Yang, Yixiang Chen, Yuan Xu +14
Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demonstrating remarkable potential for…
Certain Head, Uncertain Tail: Expert-Sample for Test-Time Scaling in Fine-Grained MoE
Yuanteng Chen, Peisong Wang, Nanxin Zeng +5
Test-time scaling improves LLM performance by generating multiple candidate solutions, yet token-level sampling requires temperature tuning that trades off diversity against stabil…
LERA: Reinstating Judgment as a Structural Precondition for Execution in Automated Systems
Jing, Liu
As automated systems increasingly transition from decision support to direct execution, the problem of accountability shifts from decision quality to execution legitimacy. While op…
MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering
Chuanzhe Guo, Jingjing Wu, Sijun He +10
The evolution of Large Language Model (LLM) agents for software engineering (SWE) is constrained by the scarcity of verifiable datasets, a bottleneck stemming from the complexity o…
PIGEON: VLM-Driven Object Navigation via Points of Interest Selection
Cheng Peng, Zhenzhe Zhang, Xiaobao Wei +7
Object navigation in unseen indoor environments requires agents to perform semantic search under partial observability. Vision-language models (VLMs) provide strong semantic-spatia…
Layer Specialization Underlying Compositional Reasoning in Transformers
Jing Liu
Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investi…
A Survey on Parallel Reasoning
Ziqi Wang, Boye Niu, Zipeng Gao +10
With the increasing capabilities of Large Language Models (LLMs), parallel reasoning has emerged as a new inference paradigm that enhances reasoning robustness by concurrently expl…
Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
Ryan Solgi, Parsa Madinei, Jiayi Tian +4
Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment.…
Circuit-Aware Reward Training: A Mechanistic Framework for Longtail Robustness in RLHF
Jing Liu
Reinforcement Learning from Human Feedback (RLHF) reward models exhibit systematic failures on longtail distributions, leading to reward hacking and misalignment. We propose a mech…
A2R: An Asymmetric Two-Stage Reasoning Framework for Parallel Reasoning
Ziqi Wang, Boye Niu, Zhongli Li +7
Recent Large Reasoning Models have achieved significant improvements in complex task-solving capabilities by allocating more computation at the inference stage with a "thinking lon…
Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
Junliang Li, Yucheng Wang, Yan Chen +5
Hallucination in large language models (LLMs) during long-form generation remains difficult to address under existing reinforcement learning from human feedback (RLHF) frameworks,…
ViFP: A Framework for Visual False Positive Detection to Enhance Reasoning Reliability in VLMs
Ben Zhang, LuLu Yu, Lei Gao +3
During reasoning in vision-language models (VLMs), false positive (FP) reasoning occurs when a model produces the correct answer but follows an incorrect reasoning path, resulting…
The Amazon Nova Family of Models: Technical Report and Model Card
Amazon AGI, Aaron Langford, Aayush Shah +783
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highl…
Can AI automatically analyze public opinion? A LLM agents-based agentic pipeline for timely public opinion analysis
Jing Liu, Xinxing Ren, Yanmeng Xu +1
This study proposes and implements the first LLM agents based agentic pipeline for multi task public opinion analysis. Unlike traditional methods, it offers an end-to-end, fully au…
Empirical Computation: Prompting versus Programming
Eric Tang, Jing Liu, Marcel Böhme
Large Language Models (LLM) can solve *any* computational problem *without* an algorithm in a runtime *independent* of the computational complexity of that problem. Instead of spec…
Evaluating LLM-Based Regression Test Generation
Jing Liu, Seongmin Lee, Eleonora Losiouk +1
Large Language Models (LLMs) have shown tremendous promise in automated software engineering. In this paper, we investigate LLMs for just-in-time regression test generation for pro…
Gap Preserving Distillation by Building Bidirectional Mappings with A Dynamic Teacher
Yong Guo, Shulian Zhang, Haolin Pan +3
Knowledge distillation aims to transfer knowledge from a large teacher model to a compact student counterpart, often coming with a significant performance gap between them. We find…
LLM4Fuzz: Guided Fuzzing of Smart Contracts with Large Language Models
Chaofan Shou, Jing Liu, Doudou Lu +1
As blockchain platforms grow exponentially, millions of lines of smart contract code are being deployed to manage extensive digital assets. However, vulnerabilities in this mission…