arXiv:2503.16771v2 Announce Type: replace-cross Abstract: As Large Language Models for Code (LM4Code) become integral to software engineering, establishing trust in their output becomes critical. However, standard accuracy metrics obscure the underlying reasoning of generative models, offering little insight into how…
arXiv:2601.09071v1 Announce Type: new Abstract: The existence of multiple, equally accurate models for a given predictive task leads to predictive multiplicity, where a “Rashomon set” of models achieve similar accuracy but diverges in their individual predictions. This inconsistency undermines trust…
arXiv:2508.10337v2 Announce Type: replace-cross Abstract: This paper describes the solutions of the Dianping-Trust-Safety team for the META CRAG-MM challenge. The challenge requires building a comprehensive retrieval-augmented generation system capable for multi-modal multi-turn question answering. The competition consists of three tasks:…
arXiv:2601.09076v1 Announce Type: new Abstract: Split Federated Learning (SFL) enables collaborative training between resource-constrained edge devices and a compute-rich server. Communication overhead is a central issue in SFL and can be mitigated with auxiliary networks. Yet, the fundamental client-side computation…
arXiv:2512.17340v2 Announce Type: replace-cross Abstract: Fair regression methods have the potential to mitigate societal bias concerns in health care, but there has been little work on penalized fair regression when multiple groups experience such bias. We propose a general regression…
arXiv:2601.09083v1 Announce Type: new Abstract: We present Speculative Rollout with Tree-Structured Cache (SRT), a simple, model-free approach to accelerate on-policy reinforcement learning (RL) for language models without sacrificing distributional correctness. SRT exploits the empirical similarity of rollouts for the same…
arXiv:2502.20580v4 Announce Type: replace Abstract: Training deep neural networks typically relies on backpropagating high dimensional error signals a computationally intensive process with little evidence supporting its implementation in the brain. However, since most tasks involve low-dimensional outputs, we propose that…
arXiv:2601.09085v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance on multiple completions per prompt makes training computationally expensive. Although recent work has reduced the number of…
arXiv:2601.09088v1 Announce Type: new Abstract: In this report, we introduce DASD-4B-Thinking, a lightweight yet highly capable, fully open-source reasoning model. It achieves SOTA performance among open-source models of comparable scale across challenging benchmarks in mathematics, scientific reasoning, and code generation…
arXiv:2507.22500v2 Announce Type: replace Abstract: Forecast reconciliation, an ex-post technique applied to forecasts that must satisfy constraints, has been a prominent topic in the forecasting literature over the past two decades. Recently, several efforts have sought to extend reconciliation methods…
