MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination

Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation (RAG) systems. While existing hallucination detection methods employ LLM-as-a-judge to verify LLM outputs against retrieved evidence, they suffer from inherent confirmation bias, where the verifier inadvertently reproduces the errors of the original generation. To address this, we introduce Multi-Agent Reinforced Self-Check for Hallucination (MARCH), a framework that enforces rigorous factual alignment by leveraging deliberate information asymmetry. MARCH orchestrates a collaborative pipeline of three specialized agents: a Solver, a Proposer, and a Checker. The Solver generates an initial RAG response, which the Proposer decomposes into claim-level verifiable atomic propositions. Crucially, the Checker validates these propositions against retrieved evidence in isolation, deprived of the Solver's original output. This well-crafted information asymmetry scheme breaks the cycle of self-confirmation bias. By training this pipeline with multi-agent reinforcement learning (MARL), we enable the agents to co-evolve and optimize factual adherence. Extensive experiments across hallucination benchmarks demonstrate that MARCH substantially reduces hallucination rates. Notably, an 8B-parameter LLM equipped with MARCH achieves performance competitive with powerful closed-source models. MARCH paves a scalable path for factual self-improvement of LLMs through co-evolution. The code is at https://github.com/Qwen-Applications/MARCH.

NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection

Despite the remarkable progress in open-vocabulary object detection (OVD), a significant gap remains between the training and testing phases. During training, the RPN and RoI heads often misclassify unlabeled novel-category objects as background, causing some proposals to be prematurely filtered out by the RPN while others are further misclassified by the RoI head. During testing, these proposals again receive low scores and are removed in post-processing, leading to a significant drop in recall and ultimately weakening novel-category detection performance.To address these issues, we propose a novel training framework-NoOVD-which innovatively integrates a self-distillation mechanism grounded in the knowledge of frozen vision-language models (VLMs). Specifically, we design K-FPN, which leverages the pretrained knowledge of VLMs to guide the model in discovering novel-category objects and facilitates knowledge distillation-without requiring additional data-thus preventing forced alignment of novel objects with background.Additionally, we introduce R-RPN, which adjusts the confidence scores of proposals during inference to improve the recall of novel-category objects. Cross-dataset evaluations on OV-LVIS, OV-COCO, and Objects365 demonstrate that our approach consistently achieves superior performance across multiple metrics.

Gradients Must Earn Their Influence: Unifying SFT with Generalized Entropic Objectives

Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy supervision and disrupt robust priors, and (ii) uniform weighting provides weak sharpening when the model is already confident. Existing methods fail to resolve the resulting plasticity--stability dilemma, often suppressing necessary learning signals alongside harmful ones. To address this issue, we unify token-level SFT objectives within a generalized deformed-log family and expose a universal gate $\times$ error gradient structure, where the gate controls how much the model trusts its current prediction. By employing the Cayley transform, we map the model's continuously evolving uncertainty onto a continuous focus trajectory, which enables seamless interpolation between scenarios involving uncertain novel concepts and those involving well-established knowledge. We then introduce Dynamic Entropy Fine-Tuning (DEFT), a parameter-free objective that modulates the trust gate using distribution concentration (Rényi-2 entropy) as a practical proxy for the model's predictive state. Extensive experiments and analyses demonstrate that DEFT achieves a better balance between exploration and exploitation, leading to improved overall performance.

Intersectional Fairness in Vision-Language Models for Medical Image Disease Classification

Medical artificial intelligence (AI) systems, particularly multimodal vision-language models (VLM), often exhibit intersectional biases where models are systematically less confident in diagnosing marginalised patient subgroups. Such bias can lead to higher rates of inaccurate and missed diagnoses due to demographically skewed data and divergent distributions of diagnostic certainty. Current fairness interventions frequently fail to address these gaps or compromise overall diagnostic performance to achieve statistical parity among the subgroups. In this study, we developed Cross-Modal Alignment Consistency (CMAC-MMD), a training framework that standardises diagnostic certainty across intersectional patient subgroups. Unlike traditional debiasing methods, this approach equalises the model's decision confidence without requiring sensitive demographic data during clinical inference. We evaluated this approach using 10,015 skin lesion images (HAM10000) with external validation on 12,000 images (BCN20000), and 10,000 fundus images for glaucoma detection (Harvard-FairVLMed), stratifying performance by intersectional age, gender, and race attributes. In the dermatology cohort, the proposed method reduced the overall intersectional missed diagnosis gap (difference in True Positive Rate, $Δ$TPR) from 0.50 to 0.26 while improving the overall Area Under the Curve (AUC) from 0.94 to 0.97 compared to standard training. Similarly, for glaucoma screening, the method reduced $Δ$TPR from 0.41 to 0.31, achieving a better AUC of 0.72 (vs. 0.71 baseline). This establishes a scalable framework for developing high-stakes clinical decision support systems that are both accurate and can perform equitably across diverse patient subgroups, ensuring reliable performance without increasing privacy risks.

LabelGS: Label-Aware 3D Gaussian Splatting for 3D Scene Segmentation

3D Gaussian Splatting (3DGS) has emerged as a novel explicit representation for 3D scenes, offering both high-fidelity reconstruction and efficient rendering. However, 3DGS lacks 3D segmentation ability, which limits its applicability in tasks that require scene understanding. The identification and isolating of specific object components is crucial. To address this limitation, we propose Label-aware 3D Gaussian Splatting (LabelGS), a method that augments the Gaussian representation with object label.LabelGS introduces cross-view consistent semantic masks for 3D Gaussians and employs a novel Occlusion Analysis Model to avoid overfitting occlusion during optimization, Main Gaussian Labeling model to lift 2D semantic prior to 3D Gaussian and Gaussian Projection Filter to avoid Gaussian label conflict. Our approach achieves effective decoupling of Gaussian representations and refines the 3DGS optimization process through a random region sampling strategy, significantly improving efficiency. Extensive experiments demonstrate that LabelGS outperforms previous state-of-the-art methods, including Feature-3DGS, in the 3D scene segmentation task. Notably, LabelGS achieves a remarkable 22X speedup in training compared to Feature-3DGS, at a resolution of 1440X1080. Our code will be at https://github.com/garrisonz/LabelGS.

Emergent morphogenesis via planar fabrication enabled by a reduced model of composites

The ability to engineer complex three-dimensional shapes from planar sheets with precise, programmable control underpins emerging technologies in soft robotics, reconfigurable devices, and functional materials. Here, we present a reduced-order numerical and experimental framework for a bilayer system consisting of a stimuli-responsive thermoplastic sheet (Shrinky Dink) bonded to a kirigami-patterned, inert plastic layer. Upon uniform heating, the active layer contracts while the patterned layer constrains in-plane stretch but allows out-of-plane bending, yielding programmable 3D morphologies from simple planar precursors. Our approach enables efficient computational design and scalable manufacturing of 3D forms with a single-layer reduced model that captures the coupled mechanics of stretching and bending. Unlike traditional bilayer modeling, our framework collapses the multilayer composite into a single layer of nodes and elements, reducing the degrees of freedom and enabling simulation on a 2D geometry. This is achieved by introducing a novel energy formulation that captures the coupling between in-plane stretch mismatch and out-of-plane bending - extending beyond simple isotropic linear elastic models. Experimentally, we establish a fully planar, repeatable fabrication protocol using a stimuli-responsive thermoplastic and a laser-cut inert plastic layer. The programmed strain mismatch drives an array of 3D morphologies, such as bowls, canoes, and flower petals, all verified by both simulation and physical prototypes.

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers

Large Language Models have achieved remarkable success in natural language processing tasks, with Reinforcement Learning playing a key role in adapting them to specific applications. However, obtaining ground truth answers for training LLMs in mathematical problem-solving is often challenging, costly, and sometimes unfeasible. This research delves into the utilization of format and length as surrogate signals to train LLMs for mathematical problem-solving, bypassing the need for traditional ground truth answers.Our study shows that a reward function centered on format correctness alone can yield performance improvements comparable to the standard GRPO algorithm in early phases. Recognizing the limitations of format-only rewards in the later phases, we incorporate length-based rewards. The resulting GRPO approach, leveraging format-length surrogate signals, not only matches but surpasses the performance of the standard GRPO algorithm relying on ground truth answers in certain scenarios, achieving 40.0\% accuracy on AIME2024 with a 7B base model. Through systematic exploration and experimentation, this research not only offers a practical solution for training LLMs to solve mathematical problems and reducing the dependence on extensive ground truth data collection, but also reveals the essence of why our label-free approach succeeds: base model is like an excellent student who has already mastered mathematical and logical reasoning skills, but performs poorly on the test paper, it simply needs to develop good answering habits to achieve outstanding results in exams , in other words, to unlock the capabilities it already possesses.

FairZK: A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge

With the rise of machine learning techniques, ensuring the fairness of decisions made by machine learning algorithms has become of great importance in critical applications. However, measuring fairness often requires full access to the model parameters, which compromises the confidentiality of the models. In this paper, we propose a solution using zero-knowledge proofs, which allows the model owner to convince the public that a machine learning model is fair while preserving the secrecy of the model. To circumvent the efficiency barrier of naively proving machine learning inferences in zero-knowledge, our key innovation is a new approach to measure fairness only with model parameters and some aggregated information of the input, but not on any specific dataset. To achieve this goal, we derive new bounds for the fairness of logistic regression and deep neural network models that are tighter and better reflecting the fairness compared to prior work. Moreover, we develop efficient zero-knowledge proof protocols for common computations involved in measuring fairness, including the spectral norm of matrices, maximum, absolute value, and fixed-point arithmetic. We have fully implemented our system, FairZK, that proves machine learning fairness in zero-knowledge. Experimental results show that FairZK is significantly faster than the naive approach and an existing scheme that use zero-knowledge inferences as a subroutine. The prover time is improved by 3.1x--1789x depending on the size of the model and the dataset. FairZK can scale to a large model with 47 million parameters for the first time, and generates a proof for its fairness in 343 seconds. This is estimated to be 4 orders of magnitude faster than existing schemes, which only scale to small models with hundreds to thousands of parameters.

A Scalable System to Prove Machine Learning Fairness in Zero-Knowledge

With the rise of machine learning techniques, ensuring the fairness of decisions made by machine learning algorithms has become of great importance in critical applications. However, measuring fairness often requires full access to the model parameters, which compromises the confidentiality of the models. In this paper, we propose a solution using zero-knowledge proofs, which allows the model owner to convince the public that a machine learning model is fair while preserving the secrecy of the model. To circumvent the efficiency barrier of naively proving machine learning inferences in zero-knowledge, our key innovation is a new approach to measure fairness only with model parameters and some aggregated information of the input, but not on any specific dataset. To achieve this goal, we derive new bounds for the fairness of logistic regression and deep neural network models that are tighter and better reflecting the fairness compared to prior work. Moreover, we develop efficient zero-knowledge proof protocols for common computations involved in measuring fairness, including the spectral norm of matrices, maximum, absolute value, and fixed-point arithmetic. We have fully implemented our system, FairZK, that proves machine learning fairness in zero-knowledge. Experimental results show that FairZK is significantly faster than the naive approach and an existing scheme that use zero-knowledge inferences as a subroutine. The prover time is improved by 3.1x--1789x depending on the size of the model and the dataset. FairZK can scale to a large model with 47 million parameters for the first time, and generates a proof for its fairness in 343 seconds. This is estimated to be 4 orders of magnitude faster than existing schemes, which only scale to small models with hundreds to thousands of parameters.

Baichuan-M1: Pushing the Medical Capability of Large Language Models

The current generation of large language models (LLMs) is typically designed for broad, general-purpose applications, while domain-specific LLMs, especially in vertical fields like medicine, remain relatively scarce. In particular, the development of highly efficient and practical LLMs for the medical domain is challenging due to the complexity of medical knowledge and the limited availability of high-quality data. To bridge this gap, we introduce Baichuan-M1, a series of large language models specifically optimized for medical applications. Unlike traditional approaches that simply continue pretraining on existing models or apply post-training to a general base model, Baichuan-M1 is trained from scratch with a dedicated focus on enhancing medical capabilities. Our model is trained on 20 trillion tokens and incorporates a range of effective training methods that strike a balance between general capabilities and medical expertise. As a result, Baichuan-M1 not only performs strongly across general domains such as mathematics and coding but also excels in specialized medical fields. We have open-sourced Baichuan-M1-14B, a mini version of our model, which can be accessed through the following links.