Reinforcement-aware Knowledge Distillation for LLM Reasoning

Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most existing knowledge distillation (KD) methods are designed for supervised fine-tuning (SFT), relying on fixed teacher traces or teacher-student Kullback-Leibler (KL) divergence-based regularization. When combined with RL, these approaches often suffer from distribution mismatch and objective interference: teacher supervision may not align with the student's evolving rollout distribution, and the KL regularizer can compete with reward maximization and require careful loss balancing. To address these issues, we propose RL-aware distillation (RLAD), which performs selective imitation during RL -- guiding the student toward the teacher only when it improves the current policy update. Our core component, Trust Region Ratio Distillation (TRRD), replaces the teacher-student KL regularizer with a PPO/GRPO-style likelihood-ratio objective anchored to a teacher--old-policy mixture, yielding advantage-aware, trust-region-bounded distillation on student rollouts and naturally balancing exploration, exploitation, and imitation. Across diverse logic reasoning and math benchmarks, RLAD consistently outperforms offline distillation, standard GRPO, and KL-based on-policy teacher-student knowledge distillation.

AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation

Referring Image Segmentation (RIS) aims to segment an object in an image identified by a natural language expression. The paper introduces Alignment-Aware Masked Learning (AML), a training strategy to enhance RIS by explicitly estimating pixel-level vision-language alignment, filtering out poorly aligned regions during optimization, and focusing on trustworthy cues. This approach results in state-of-the-art performance on RefCOCO datasets and also enhances robustness to diverse descriptions and scenarios

Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

Classifier-free guidance (CFG) has helped diffusion models achieve great conditional generation in various fields. Recently, more diffusion guidance methods have emerged with improved generation quality and human preference. However, can these emerging diffusion guidance methods really achieve solid and significant improvements? In this paper, we rethink recent progress on diffusion guidance. Our work mainly consists of four contributions. First, we reveal a critical evaluation pitfall that common human preference models exhibit a strong bias towards large guidance scales. Simply increasing the CFG scale can easily improve quantitative evaluation scores due to strong semantic alignment, even if image quality is severely damaged (e.g., oversaturation and artifacts). Second, we introduce a novel guidance-aware evaluation (GA-Eval) framework that employs effective guidance scale calibration to enable fair comparison between current guidance methods and CFG by identifying the effects orthogonal and parallel to CFG effects. Third, motivated by the evaluation pitfall, we design Transcendent Diffusion Guidance (TDG) method that can significantly improve human preference scores in the conventional evaluation framework but actually does not work in practice. Fourth, in extensive experiments, we empirically evaluate recent eight diffusion guidance methods within the conventional evaluation framework and the proposed GA-Eval framework. Notably, simply increasing the CFG scales can compete with most studied diffusion guidance methods, while all methods suffer severely from winning rate degradation over standard CFG. Our work would strongly motivate the community to rethink the evaluation paradigm and future directions of this field.

Reinforced Curriculum Pre-Alignment for Domain-Adaptive VLMs

Vision-Language Models (VLMs) demonstrate remarkable general-purpose capabilities but often fall short in specialized domains such as medical imaging or geometric problem-solving. Supervised Fine-Tuning (SFT) can enhance performance within a target domain, but it typically causes catastrophic forgetting, limiting its generalization. The central challenge, therefore, is to adapt VLMs to new domains while preserving their general-purpose capabilities. Continual pretraining is effective for expanding knowledge in Large Language Models (LLMs), but it is less feasible for VLMs due to prohibitive computational costs and the unavailability of pretraining data for most open-source models. This necessitates efficient post-training adaptation methods. Reinforcement learning (RL)-based approaches such as Group Relative Policy Optimization (GRPO) have shown promise in preserving general abilities, yet they often fail in domain adaptation scenarios where the model initially lacks sufficient domain knowledge, leading to optimization collapse. To bridge this gap, we propose Reinforced Curriculum Pre-Alignment (RCPA), a novel post-training paradigm that introduces a curriculum-aware progressive modulation mechanism. In the early phase, RCPA applies partial output constraints to safely expose the model to new domain concepts. As the model's domain familiarity increases, training gradually transitions to full generation optimization, refining responses and aligning them with domain-specific preferences. This staged adaptation balances domain knowledge acquisition with the preservation of general multimodal capabilities. Extensive experiments across specialized domains and general benchmarks validate the effectiveness of RCPA, establishing a practical pathway toward building high-performing and domain-adaptive VLMs.

Optimizing Few-Step Generation with Adaptive Matching Distillation

Distribution Matching Distillation (DMD) is a powerful acceleration paradigm, yet its stability is often compromised in Forbidden Zone, regions where the real teacher provides unreliable guidance while the fake teacher exerts insufficient repulsive force. In this work, we propose a unified optimization framework that reinterprets prior art as implicit strategies to avoid these corrupted regions. Based on this insight, we introduce Adaptive Matching Distillation (AMD), a self-correcting mechanism that utilizes reward proxies to explicitly detect and escape Forbidden Zones. AMD dynamically prioritizes corrective gradients via structural signal decomposition and introduces Repulsive Landscape Sharpening to enforce steep energy barriers against failure mode collapse. Extensive experiments across image and video generation tasks (e.g., SDXL, Wan2.1) and rigorous benchmarks (e.g., VBench, GenEval) demonstrate that AMD significantly enhances sample fidelity and training robustness. For instance, AMD improves the HPSv2 score on SDXL from 30.64 to 31.25, outperforming state-of-the-art baselines. These findings validate that explicitly rectifying optimization trajectories within Forbidden Zones is essential for pushing the performance ceiling of few-step generative models.

Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global semantic consistency and implicit logical constraints beyond local similarity. Existing reward modeling approaches have clear limitations. Discriminative reward models align well with human preferences but struggle with complex semantics due to limited reasoning supervision. Generative reward models offer stronger semantic understanding and reasoning, but they are costly at inference time and difficult to align directly with human preferences. To this end, we propose Joint Reward Modeling (JRM), which jointly optimizes preference learning and language modeling on a shared vision-language backbone. This approach internalizes the semantic and reasoning capabilities of generative models into efficient discriminative representations, enabling fast and accurate evaluation. JRM achieves state-of-the-art results on MMRB2 and EditReward-Bench, and significantly improves stability and performance in downstream online reinforcement learning. These results show that joint training effectively bridges efficiency and semantic understanding in reward modeling.

SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning

Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Existing evaluators frequently struggle with a critical perception gap we term "Attention Collapse," where models neglect cross-image comparisons and fail to capture fine-grained details, resulting in inaccurate perception and miscalibrated scores. To address these limitations, we propose SpatialReward, a reward model that enforces precise verification via explicit spatial reasoning. By anchoring reasoning to predicted edit regions, SpatialReward grounds semantic judgments in pixel-level evidence, significantly enhancing evaluative accuracy. Trained on a curated 260k spatial-aware dataset, our model achieves state-of-the-art performance on MMRB2 and EditReward-Bench, and outperforms proprietary evaluators on our proposed MultiEditReward-Bench. Furthermore, SpatialReward serves as a robust signal in online RL, boosting OmniGen2 by +0.90 on GEdit-Bench--surpassing the leading discriminative model and doubling the gain of GPT-4.1 (+0.45). These results demonstrate that spatial reasoning is essential for unlocking effective alignment in image editing.

Evolutionary Generation of Multi-Agent Systems

Large language model (LLM)-based multi-agent systems (MAS) show strong promise for complex reasoning, planning, and tool-augmented tasks, but designing effective MAS architectures remains labor-intensive, brittle, and hard to generalize. Existing automatic MAS generation methods either rely on code generation, which often leads to executability and robustness failures, or impose rigid architectural templates that limit expressiveness and adaptability. We propose Evolutionary Generation of Multi-Agent Systems (EvoMAS), which formulates MAS generation as structured configuration generation. EvoMAS performs evolutionary generation in configuration space. Specifically, EvoMAS selects initial configurations from a pool, applies feedback-conditioned mutation and crossover guided by execution traces, and iteratively refines both the candidate pool and an experience memory. We evaluate EvoMAS on diverse benchmarks, including BBEH, SWE-Bench, and WorkBench, covering reasoning, software engineering, and tool-use tasks. EvoMAS consistently improves task performance over both human-designed MAS and prior automatic MAS generation methods, while producing generated systems with higher executability and runtime robustness. EvoMAS outperforms the agent evolution method EvoAgent by +10.5 points on BBEH reasoning and +7.1 points on WorkBench. With Claude-4.5-Sonnet, EvoMAS also reaches 79.1% on SWE-Bench-Verified, matching the top of the leaderboard.

Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization

Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generation models, the KV cache grows with generation history and quickly dominates GPU memory, often exceeding 30 GB, preventing deployment on widely available hardware. More critically, constrained KV cache budgets restrict the effective working memory, directly degrading long horizon consistency in identity, layout, and motion. To address this challenge, we present Quant VideoGen (QVG), a training free KV cache quantization framework for autoregressive video diffusion models. QVG leverages video spatiotemporal redundancy through Semantic Aware Smoothing, producing low magnitude, quantization friendly residuals. It further introduces Progressive Residual Quantization, a coarse to fine multi stage scheme that reduces quantization error while enabling a smooth quality memory trade off. Across LongCat Video, HY WorldPlay, and Self Forcing benchmarks, QVG establishes a new Pareto frontier between quality and memory efficiency, reducing KV cache memory by up to 7.0 times with less than 4% end to end latency overhead while consistently outperforming existing baselines in generation quality.

A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous Driving

End-to-end autonomous driving is increasingly adopting a multimodal planning paradigm that generates multiple trajectory candidates and selects the final plan, making candidate-set design critical. A fixed trajectory vocabulary provides stable coverage in routine driving but often misses optimal solutions in complex interactions, while scene-adaptive refinement can cause over-correction in simple scenarios by unnecessarily perturbing already strong vocabulary trajectories.We propose CdDrive, which preserves the original vocabulary candidates and augments them with scene-adaptive candidates generated by vocabulary-conditioned diffusion denoising. Both candidate types are jointly scored by a shared selection module, enabling reliable performance across routine and highly interactive scenarios. We further introduce HATNA (Horizon-Aware Trajectory Noise Adapter) to improve the smoothness and geometric continuity of diffusion candidates via temporal smoothing and horizon-aware noise modulation. Experiments on NAVSIM v1 and NAVSIM v2 demonstrate leading performance, and ablations verify the contribution of each component.