DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization

Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these models suffer from overthinking, generating unnecessarily long and redundant reasoning even for simple questions, which substantially increases computational cost and response latency. While existing methods incorporate length rewards to GRPO to promote concise reasoning, they incur significant performance degradation. We identify the root cause: when rewards for correct but long rollouts are penalized, GRPO's group-relative advantage function can assign them negative advantages, actively discouraging valid reasoning. To overcome this, we propose Decoupled Reward Policy Optimization (DRPO), a novel framework that decouples the length-based learning signal of correct rollouts from incorrect ones. DRPO ensures that reward signals for correct rollouts are normalized solely within the positive group, shielding them from interference by negative samples. The DRPO's objective is grounded in integrating an optimized positive data distribution, which maximizes length-based rewards under a KL regularization, into a discriminative objective. We derive a closed-form solution for this distribution, enabling efficient computation of the objective and its gradients using only on-policy data and importance weighting. Of independent interest, this formulation is general and can incorporate other preference rewards of positive data beyond length. Experiments on mathematical reasoning tasks demonstrate DRPO's significant superiority over six efficient reasoning baselines. Notably, with a 1.5B model, our method achieves 77\% length reduction with only 1.1\% performance loss on simple questions like GSM8k dataset, while the follow-up baseline sacrifices 4.3\% for 68\% length reduction.

HART: Human Aligned Reconstruction Transformer

We introduce HART, a unified framework for sparse-view human reconstruction. Given a small set of uncalibrated RGB images of a person as input, it outputs a watertight clothed mesh, the aligned SMPL-X body mesh, and a Gaussian-splat representation for photorealistic novel-view rendering. Prior methods for clothed human reconstruction either optimize parametric templates, which overlook loose garments and human-object interactions, or train implicit functions under simplified camera assumptions, limiting applicability in real scenes. In contrast, HART predicts per-pixel 3D point maps, normals, and body correspondences, and employs an occlusion-aware Poisson reconstruction to recover complete geometry, even in self-occluded regions. These predictions also align with a parametric SMPL-X body model, ensuring that reconstructed geometry remains consistent with human structure while capturing loose clothing and interactions. These human-aligned meshes initialize Gaussian splats to further enable sparse-view rendering. While trained on only 2.3K synthetic scans, HART achieves state-of-the-art results: Chamfer Distance improves by 18-23 percent for clothed-mesh reconstruction, PA-V2V drops by 6-27 percent for SMPL-X estimation, LPIPS decreases by 15-27 percent for novel-view synthesis on a wide range of datasets. These results suggest that feed-forward transformers can serve as a scalable model for robust human reconstruction in real-world settings. Code and models will be released.

Time-Aware World Model for Adaptive Prediction and Control

In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, {\Delta}t, and training over a diverse range of {\Delta}t values -- rather than sampling at a fixed time-step -- TAWM learns both high- and low-frequency task dynamics across diverse control problems. Grounded in the information-theoretic insight that the optimal sampling rate depends on a system's underlying dynamics, this time-aware formulation improves both performance and data efficiency. Empirical evaluations show that TAWM consistently outperforms conventional models across varying observation rates in a variety of control tasks, using the same number of training samples and iterations. Our code can be found online at: github.com/anh-nn01/Time-Aware-World-Model.

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective under a binary reward setting and reveal an inherent limitation of question-level difficulty bias. We also identify a connection between GRPO and traditional discriminative methods in supervised learning. Motivated by these insights, we introduce a new Discriminative Constrained Optimization (DisCO) framework for reinforcing LRMs, grounded in the principle of discriminative learning. The main differences between DisCO and GRPO and its recent variants are: (1) it replaces the group relative objective with a discriminative objective defined by a scoring function; (2) it abandons clipping-based surrogates in favor of non-clipping RL surrogate objectives used as scoring functions; (3) it employs a simple yet effective constrained optimization approach to enforce the KL divergence constraint, ensuring stable training. As a result, DisCO offers notable advantages over GRPO and its variants: (i) it completely eliminates difficulty bias by adopting discriminative objectives; (ii) it addresses the entropy instability in GRPO and its variants through the use of non-clipping scoring functions and a constrained optimization approach; (iii) it allows the incorporation of advanced discriminative learning techniques to address data imbalance, where a significant number of questions have more negative than positive generated answers during training. Our experiments on enhancing the mathematical reasoning capabilities of SFT-finetuned models show that DisCO significantly outperforms GRPO and its improved variants such as DAPO, achieving average gains of 7\% over GRPO and 6\% over DAPO across six benchmark tasks for an 1.5B model.

Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws

This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or weighting, named $\textbf{model steering}$. While ad-hoc methods have been used in various contexts, including the training of large foundation models, its underlying principles remain insufficiently understood, leading to sub-optimal performance. In this work, we propose a theory-driven framework for model steering called $\textbf{DRRho risk minimization}$, which is rooted in Distributionally Robust Optimization (DRO). Through a generalization analysis, we provide theoretical insights into why this approach improves generalization and data efficiency compared to training without a reference model. To the best of our knowledge, this is the first time such theoretical insights are provided for the new learning paradigm, which significantly enhance our understanding and practice of model steering. Building on these insights and the connection between contrastive learning and DRO, we introduce a novel method for Contrastive Language-Image Pretraining (CLIP) with a reference model, termed DRRho-CLIP. Extensive experiments validate the theoretical insights, reveal a superior scaling law compared to CLIP without a reference model, and demonstrate its strength over existing heuristic approaches.

AUKT: Adaptive Uncertainty-Guided Knowledge Transfer with Conformal Prediction

Knowledge transfer between teacher and student models has proven effective across various machine learning applications. However, challenges arise when the teacher's predictions are noisy, or the data domain during student training shifts from the teacher's pretraining data. In such scenarios, blindly relying on the teacher's predictions can lead to suboptimal knowledge transfer. To address these challenges, we propose a novel and universal framework, Adaptive Uncertainty-guided Knowledge Transfer ($\textbf{AUKT}$), which leverages Conformal Prediction (CP) to dynamically adjust the student's reliance on the teacher's guidance based on the teacher's prediction uncertainty. CP is a distribution-free, model-agnostic approach that provides reliable prediction sets with statistical coverage guarantees and minimal computational overhead. This adaptive mechanism mitigates the risk of learning undesirable or incorrect knowledge. We validate the proposed framework across diverse applications, including image classification, imitation-guided reinforcement learning, and autonomous driving. Experimental results consistently demonstrate that our approach improves performance, robustness and transferability, offering a promising direction for enhanced knowledge transfer in real-world applications.

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

Multi-modality learning has become a crucial technique for improving the performance of machine learning applications across domains such as autonomous driving, robotics, and perception systems. While existing frameworks such as Auxiliary Modality Learning (AML) effectively utilize multiple data sources during training and enable inference with reduced modalities, they primarily operate in a single-agent context. This limitation is particularly critical in dynamic environments, such as connected autonomous vehicles (CAV), where incomplete data coverage can lead to decision-making blind spots. To address these challenges, we propose Collaborative Auxiliary Modality Learning ($\textbf{CAML}$), a novel multi-agent multi-modality framework that enables agents to collaborate and share multimodal data during training while allowing inference with reduced modalities per agent during testing. We systematically analyze the effectiveness of $\textbf{CAML}$ from the perspective of uncertainty reduction and data coverage, providing theoretical insights into its advantages over AML. Experimental results in collaborative decision-making for CAV in accident-prone scenarios demonstrate that \ours~achieves up to a ${\bf 58.13}\%$ improvement in accident detection. Additionally, we validate $\textbf{CAML}$ on real-world aerial-ground robot data for collaborative semantic segmentation, achieving up to a ${\bf 10.61}\%$ improvement in mIoU.

Search for Efficient Large Language Models

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting memory reduction and inference acceleration, which underscore the redundancy in LLMs. However, most model compression techniques concentrate on weight optimization, overlooking the exploration of optimal architectures. Besides, traditional architecture search methods, limited by the elevated complexity with extensive parameters, struggle to demonstrate their effectiveness on LLMs. In this paper, we propose a training-free architecture search framework to identify optimal subnets that preserve the fundamental strengths of the original LLMs while achieving inference acceleration. Furthermore, after generating subnets that inherit specific weights from the original LLMs, we introduce a reformation algorithm that utilizes the omitted weights to rectify the inherited weights with a small amount of calibration data. Compared with SOTA training-free structured pruning works that can generate smaller networks, our method demonstrates superior performance across standard benchmarks. Furthermore, our generated subnets can directly reduce the usage of GPU memory and achieve inference acceleration.

Prompt Mixing in Diffusion Models using the Black Scholes Algorithm

We introduce a novel approach for prompt mixing, aiming to generate images at the intersection of multiple text prompts using pre-trained text-to-image diffusion models. At each time step during diffusion denoising, our algorithm forecasts predictions w.r.t. the generated image and makes informed text conditioning decisions. To do so, we leverage the connection between diffusion models (rooted in non-equilibrium thermodynamics) and the Black-Scholes model for pricing options in Finance, and draw analogies between the variables in both contexts to derive an appropriate algorithm for prompt mixing using the Black Scholes model. Specifically, the parallels between diffusion models and the Black-Scholes model enable us to leverage properties related to the dynamics of the Markovian model derived in the Black-Scholes algorithm. Our prompt-mixing algorithm is data-efficient, meaning it does not need additional training. Furthermore, it operates without human intervention or hyperparameter tuning. We highlight the benefits of our approach by comparing it qualitatively and quantitatively to other prompt mixing techniques, including linear interpolation, alternating prompts, step-wise prompt switching, and CLIP-guided prompt selection across various scenarios such as single object per text prompt, multiple objects per text prompt and objects against backgrounds. Code is available at https://github.com/divyakraman/BlackScholesDiffusion2024.

Merino: Entropy-driven Design for Generative Language Models on IoT Devices

Generative Large Language Models (LLMs) stand as a revolutionary advancement in the modern era of artificial intelligence (AI). However, directly deploying LLMs in resource-constrained hardware, such as Internet-of-Things (IoT) devices, is difficult due to their high computational cost. In this paper, we propose a novel information-entropy framework for designing mobile-friendly generative language models. Our key design paradigm is to maximize the entropy of transformer decoders within the given computational budgets. The whole design procedure involves solving a mathematical programming (MP) problem, which can be done on the CPU within minutes, making it nearly zero-cost. We evaluate our designed models, termed MeRino, across nine NLP downstream tasks, showing their competitive performance against the state-of-the-art autoregressive transformer models under the mobile setting. Notably, MeRino achieves similar or better zero performance compared to the 350M parameter OPT while being 4.9x faster on NVIDIA Jetson Nano with 5.5x reduction in model size. Code will be made available soon.