2 citations · 2 across the 13 of their papers we have counts for
11 papers · 1 filter
SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
Xupeng Chen, Chenqian Le, Jiayi Cheng +2
A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On the sparse co-activation gr…
Multi-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence
Chenqian Le, Jiayi Cheng, Qijia He +3
Recent systems train coding agents with reinforcement learning (RL) on trajectories collected through multiple execution harnesses. However, gains under the training harnesses leav…
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
Junze Ye, Jiayi Cheng, Miao Lu +3
For LLM agents, supervised fine-tuning is not only about teacher labels' quality, but also about which interaction contexts those labels condition on. Pure behavioral cloning uses…
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
Qijia He, Jiayi Cheng, Chenqian Le +8
Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer. Existing cost-aware system…
PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Discrete masked diffusion language models support bidirectional generation and infilling, but adapting pretrained autoregressive (AR) transformers requires reconciling causal pretr…
Less Data, Better Alignment: Data-Centric Multi-Evaluator Agreement for Preference Optimization
Zhengtao Yao, Runhao Li, Xupeng Chen +12
Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +378
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
Discrete Stochastic Localization for Non-autoregressive Generation
Yunshu Wu, Jiayi Cheng, Longxuan Yu +4
Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generatio…
VehAnchor: Metadata-Free Metric Scale Recovery from Vehicle Cues in Aerial Imagery
Yifei Chen, Chenqian Le, Jiayi Cheng +1
Autonomous aerial robots operating in GPS-denied or communication-degraded environments frequently lose access to camera metadata and telemetry, leaving onboard perception systems…
Discrete Stochastic Localization for Non-autoregressive Generation
Yunshu Wu, Jiayi Cheng, Longxuan Yu +4
Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generatio…
FutureX-Pro: Extending Future Prediction to High-Value Vertical Domains
Jiashuo Liu, Siyuan Chen, Zaiyuan Wang +38
Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, Futu…