Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for improving large language models (LLMs) on reasoning tasks, with Group Relative Policy Optimization (GRPO) widely used in practice. Yet GRPO wastes substantial compute on negative groups: groups in which no sampled response is correct yield zero advantage and thus no gradient. We ask whether negative groups can be leveraged without extra supervision. Starting from a maximum-likelihood (MLE) objective in reward modeling, we show that the MLE gradient is equivalent to a policy gradient for a modified value function. This value function adds a confidence-weighted penalty on incorrect responses, imposing larger penalties on more confident mistakes. We refer to this as \textbf{L}ikelihood \textbf{E}stimation with \textbf{N}egative \textbf{S}amples (\textbf{LENS}). LENS modifies GRPO to assign non-zero, confidence-dependent rewards to incorrect generations, making negative groups informative and converting previously wasted samples into useful gradient updates. On the MATH benchmark with Llama-3.1-8B and Qwen-2.5-3B, the proposed variant consistently outperforms GRPO baseline, with significant gains on harder items. These results demonstrate a principled and practical way to "rescue" negative groups, improving efficiency and performance in RLVR.

In addition to accurate scene understanding through precise semantic segmentation of LiDAR point clouds, detecting out-of-distribution (OOD) objects, instances not encountered during training, is essential to prevent the incorrect assignment of unknown objects to known classes. While supervised OOD detection methods depend on auxiliary OOD datasets, unsupervised methods avoid this requirement but typically rely on predictive entropy, the entropy of the predictive distribution obtained by averaging over an ensemble or multiple posterior weight samples. However, these methods often conflate epistemic (model) and aleatoric (data) uncertainties, misclassifying ambiguous in distribution regions as OOD. To address this issue, we present an unsupervised OOD detection approach that employs epistemic uncertainty derived from hierarchical Bayesian modeling of Gaussian Mixture Model (GMM) parameters in the feature space of a deep neural network. Without requiring auxiliary data or additional training stages, our approach outperforms existing uncertainty-based methods on the SemanticKITTI dataset, achieving an 18\% improvement in AUROC, 22\% increase in AUPRC, and 36\% reduction in FPR95 (from 76\% to 40\%), compared to the predictive entropy approach used in prior works.

Phylogenetic trees elucidate evolutionary relationships among species, but phylogenetic inference remains challenging due to the complexity of combining continuous (branch lengths) and discrete parameters (tree topology).

Large language models (LLMs) are now available from cloud API providers in various sizes and configurations.

Differentiable structure learning is a novel line of causal discovery research that transforms the combinatorial optimization of structural models into a continuous optimization problem. However, the field has lacked feasible methods to integrate partial order constraints, a critical prior information typically used in real-world scenarios, into the differentiable structure learning framework. The main difficulty lies in adapting these constraints, typically suited for the space of total orderings, to the continuous optimization context of structure learning in the graph space. To bridge this gap, this paper formalizes a set of equivalent constraints that map partial orders onto graph spaces and introduces a plug-and-play module for their efficient application. This module preserves the equivalent effect of partial order constraints in the graph space, backed by theoretical validations of correctness and completeness. It significantly enhances the quality of recovered structures while maintaining good efficiency, which learns better structures using 90% fewer samples than the data-based method on a real-world dataset. This result, together with a comprehensive evaluation on synthetic cases, demonstrates our method's ability to effectively improve differentiable structure learning with partial orders.

Reconstructing past events requires reasoning across long time horizons.