Decoupling Continual Semantic Segmentation

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods typically employ single-stage encoder-decoder architectures where segmentation masks and class labels are tightly coupled, leading to interference between old and new class learning and suboptimal retention-plasticity balance. We introduce DecoupleCSS, a novel two-stage framework for CSS. By decoupling class-aware detection from class-agnostic segmentation, DecoupleCSS enables more effective continual learning, preserving past knowledge while learning new classes. The first stage leverages pre-trained text and image encoders, adapted using LoRA, to encode class-specific information and generate location-aware prompts. In the second stage, the Segment Anything Model (SAM) is employed to produce precise segmentation masks, ensuring that segmentation knowledge is shared across both new and previous classes. This approach improves the balance between retention and adaptability in CSS, achieving state-of-the-art performance across a variety of challenging tasks. Our code is publicly available at: https://github.com/euyis1019/Decoupling-Continual-Semantic-Segmentation.

EndoFinder: Online Lesion Retrieval for Explainable Colorectal Polyp Diagnosis Leveraging Latent Scene Representations

Colorectal cancer (CRC) remains a leading cause of cancer-related mortality, underscoring the importance of timely polyp detection and diagnosis. While deep learning models have improved optical-assisted diagnostics, they often demand extensive labeled datasets and yield "black-box" outputs with limited interpretability. In this paper, we propose EndoFinder, an online polyp retrieval framework that leverages multi-view scene representations for explainable and scalable CRC diagnosis. First, we develop a Polyp-aware Image Encoder by combining contrastive learning and a reconstruction task, guided by polyp segmentation masks. This self-supervised approach captures robust features without relying on large-scale annotated data. Next, we treat each polyp as a three-dimensional "scene" and introduce a Scene Representation Transformer, which fuses multiple views of the polyp into a single latent representation. By discretizing this representation through a hashing layer, EndoFinder enables real-time retrieval from a compiled database of historical polyp cases, where diagnostic information serves as interpretable references for new queries. We evaluate EndoFinder on both public and newly collected polyp datasets for re-identification and pathology classification. Results show that EndoFinder outperforms existing methods in accuracy while providing transparent, retrieval-based insights for clinical decision-making. By contributing a novel dataset and a scalable, explainable framework, our work addresses key challenges in polyp diagnosis and offers a promising direction for more efficient AI-driven colonoscopy workflows. The source code is available at https://github.com/ku262/EndoFinder-Scene.

Text-driven Multiplanar Visual Interaction for Semi-supervised Medical Image Segmentation

Semi-supervised medical image segmentation is a crucial technique for alleviating the high cost of data annotation. When labeled data is limited, textual information can provide additional context to enhance visual semantic understanding. However, research exploring the use of textual data to enhance visual semantic embeddings in 3D medical imaging tasks remains scarce. In this paper, we propose a novel text-driven multiplanar visual interaction framework for semi-supervised medical image segmentation (termed Text-SemiSeg), which consists of three main modules: Text-enhanced Multiplanar Representation (TMR), Category-aware Semantic Alignment (CSA), and Dynamic Cognitive Augmentation (DCA). Specifically, TMR facilitates text-visual interaction through planar mapping, thereby enhancing the category awareness of visual features. CSA performs cross-modal semantic alignment between the text features with introduced learnable variables and the intermediate layer of visual features. DCA reduces the distribution discrepancy between labeled and unlabeled data through their interaction, thus improving the model's robustness. Finally, experiments on three public datasets demonstrate that our model effectively enhances visual features with textual information and outperforms other methods. Our code is available at https://github.com/taozh2017/Text-SemiSeg.

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planning and iterative refinement features of dLLMs are particularly useful for code generation. However, current training and inference mechanisms for dLLMs in coding are still under-explored. To demystify the decoding behavior of dLLMs and unlock their potential for coding, we systematically investigate their denoising processes and reinforcement learning (RL) methods. We train a 7B dLLM, \textbf{DiffuCoder}, on 130B tokens of code. Using this model as a testbed, we analyze its decoding behavior, revealing how it differs from that of AR models: (1) dLLMs can decide how causal their generation should be without relying on semi-AR decoding, and (2) increasing the sampling temperature diversifies not only token choices but also their generation order. This diversity creates a rich search space for RL rollouts. For RL training, to reduce the variance of token log-likelihood estimates and maintain training efficiency, we propose \textbf{coupled-GRPO}, a novel sampling scheme that constructs complementary mask noise for completions used in training. In our experiments, coupled-GRPO significantly improves DiffuCoder's performance on code generation benchmarks (+4.4\% on EvalPlus) and reduces reliance on AR bias during decoding. Our work provides deeper insight into the machinery of dLLM generation and offers an effective, diffusion-native RL training framework. https://github.com/apple/ml-diffucoder.

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial redundancy, which limits the efficiency of LRMs. In this paper, we investigate RL-based approaches to promote reasoning efficiency. Specifically, we first present a unified framework that formulates various efficient reasoning methods through the lens of length-based reward shaping. Building on this perspective, we propose a novel Length-bAsed StEp Reward shaping method (LASER), which employs a step function as the reward, controlled by a target length. LASER surpasses previous methods, achieving a superior Pareto-optimal balance between performance and efficiency. Next, we further extend LASER based on two key intuitions: (1) The reasoning behavior of the model evolves during training, necessitating reward specifications that are also adaptive and dynamic; (2) Rather than uniformly encouraging shorter or longer chains of thought (CoT), we posit that length-based reward shaping should be difficulty-aware i.e., it should penalize lengthy CoTs more for easy queries. This approach is expected to facilitate a combination of fast and slow thinking, leading to a better overall tradeoff. The resulting method is termed LASER-D (Dynamic and Difficulty-aware). Experiments on DeepSeek-R1-Distill-Qwen-1.5B, DeepSeek-R1-Distill-Qwen-7B, and DeepSeek-R1-Distill-Qwen-32B show that our approach significantly enhances both reasoning performance and response length efficiency. For instance, LASER-D and its variant achieve a +6.1 improvement on AIME2024 while reducing token usage by 63%. Further analysis reveals our RL-based compression produces more concise reasoning patterns with less redundant "self-reflections". Resources are at https://github.com/hkust-nlp/Laser.

ARMOR: Adaptive Meshing with Reinforcement Optimization for Real-time 3D Monitoring in Unexposed Scenes

Unexposed environments, such as lava tubes, mines, and tunnels, are among the most complex yet strategically significant domains for scientific exploration and infrastructure development. Accurate and real-time 3D meshing of these environments is essential for applications including automated structural assessment, robotic-assisted inspection, and safety monitoring. Implicit neural Signed Distance Fields (SDFs) have shown promising capabilities in online meshing; however, existing methods often suffer from large projection errors and rely on fixed reconstruction parameters, limiting their adaptability to complex and unstructured underground environments such as tunnels, caves, and lava tubes. To address these challenges, this paper proposes ARMOR, a scene-adaptive and reinforcement learning-based framework for real-time 3D meshing in unexposed environments. The proposed method was validated across more than 3,000 meters of underground environments, including engineered tunnels, natural caves, and lava tubes. Experimental results demonstrate that ARMOR achieves superior performance in real-time mesh reconstruction, reducing geometric error by 3.96\% compared to state-of-the-art baselines, while maintaining real-time efficiency. The method exhibits improved robustness, accuracy, and adaptability, indicating its potential for advanced 3D monitoring and mapping in challenging unexposed scenarios. The project page can be found at: https://yizhezhang0418.github.io/armor.github.io/

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion

Discrete diffusion is a promising framework for modeling and generating discrete data. In this work, we present Target Concrete Score Matching (TCSM), a novel and versatile objective for training and fine-tuning discrete diffusion models. TCSM provides a general framework with broad applicability. It supports pre-training discrete diffusion models directly from data samples, and many existing discrete diffusion approaches naturally emerge as special cases of our more general TCSM framework. Furthermore, the same TCSM objective extends to post-training of discrete diffusion models, including fine-tuning using reward functions or preference data, and distillation of knowledge from pre-trained autoregressive models. These new capabilities stem from the core idea of TCSM, estimating the concrete score of the target distribution, which resides in the original (clean) data space. This allows seamless integration with reward functions and pre-trained models, which inherently only operate in the clean data space rather than the noisy intermediate spaces of diffusion processes. Our experiments on language modeling tasks demonstrate that TCSM matches or surpasses current methods. Additionally, TCSM is versatile, applicable to both pre-training and post-training scenarios, offering greater flexibility and sample efficiency.

SAGE: Steering and Refining Dialog Generation with State-Action Augmentation

Recent advances in large language models have demonstrated impressive capabilities in task-oriented applications, yet building emotionally intelligent chatbots that can engage in natural, strategic conversations remains a challenge. We present a novel approach called SAGE that uses latent variables to control long-horizon behavior in dialogue generation. At the core of our method is the State-Action Chain (SAC), which augments standard language model fine-tuning by introducing latent variables that encapsulate emotional states and conversational strategies between dialogue turns. During inference, these variables are generated before each response, enabling coarse-grained control over dialogue progression while maintaining natural interaction patterns. We also introduce a self-improvement pipeline that leverages dialogue tree search, LLM-based reward modeling, and targeted fine-tuning to optimize conversational trajectories. Our experimental results show that models trained with this approach demonstrate improved performance in emotional intelligence metrics while maintaining strong capabilities on LLM benchmarks. The discrete nature of our latent variables facilitates search-based strategies and provides a foundation for future applications of reinforcement learning to dialogue systems, where learning can occur at the state level rather than the token level.

Reversal Blessing: Thinking Backward May Outpace Thinking Forward in Multi-choice Questions

Language models usually use left-to-right (L2R) autoregressive factorization. However, L2R factorization may not always be the best inductive bias. Therefore, we investigate whether alternative factorizations of the text distribution could be beneficial in some tasks. We investigate right-to-left (R2L) training as a compelling alternative, focusing on multiple-choice questions (MCQs) as a test bed for knowledge extraction and reasoning. Through extensive experiments across various model sizes (2B-8B parameters) and training datasets, we find that R2L models can significantly outperform L2R models on several MCQ benchmarks, including logical reasoning, commonsense understanding, and truthfulness assessment tasks. Our analysis reveals that this performance difference may be fundamentally linked to multiple factors including calibration, computability and directional conditional entropy. We ablate the impact of these factors through controlled simulation studies using arithmetic tasks, where the impacting factors can be better disentangled. Our work demonstrates that exploring alternative factorizations of the text distribution can lead to improvements in LLM capabilities and provides theoretical insights into optimal factorization towards approximating human language distribution, and when each reasoning order might be more advantageous.

Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models

Recent advancements in long-context language models (LCLMs) promise to transform Retrieval-Augmented Generation (RAG) by simplifying pipelines. With their expanded context windows, LCLMs can process entire knowledge bases and perform retrieval and reasoning directly -- a capability we define as In-Context Retrieval and Reasoning (ICR^2). However, existing benchmarks like LOFT often overestimate LCLM performance by providing overly simplified contexts. To address this, we introduce ICR^2, a benchmark that evaluates LCLMs in more realistic scenarios by including confounding passages retrieved with strong retrievers. We then propose three methods to enhance LCLM performance: (1) retrieve-then-generate fine-tuning, (2) retrieval-attention-probing, which uses attention heads to filter and de-noise long contexts during decoding, and (3) joint retrieval head training alongside the generation head. Our evaluation of five well-known LCLMs on LOFT and ICR^2 demonstrates significant gains with our best approach applied to Mistral-7B: +17 and +15 points by Exact Match on LOFT, and +13 and +2 points on ICR^2, compared to vanilla RAG and supervised fine-tuning, respectively. It even outperforms GPT-4-Turbo on most tasks despite being a much smaller model.