Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain underexplored. In this paper, we provide several insights into such fine-tuning through the lens of linearization. Fine-tuned models are often implicitly encouraged to remain close to the pretrained model. By making this explicit, using an $\ell_2$-distance inductive bias in parameter space, we show that fine-tuning dynamics become equivalent to learning with the positive-definite neural tangent kernel (NTK). We specifically analyze how close the fully linear and the linearized fine-tuning optimizations are, based on the strength of the regularization. This allows us to be pragmatic about how good a model linearization is when fine-tuning large language models (LLMs). When linearization is a good model, our findings reveal a strong correlation between the eigenvalue spectrum of the NTK and the performance of model adaptation. Motivated by this, we give spectral perturbation bounds on the NTK induced by the choice of layers selected for fine-tuning.

Modern LLMs can now produce highly readable abstractive summaries, to the point that traditional automated metrics for evaluating summary quality, such as ROUGE, have saturated. However, LLMs still sometimes introduce inaccuracies into summaries, i.e., information inconsistent with or unsupported by the corresponding source. Measuring the occurrence of these often subtle factual inconsistencies automatically has proved challenging. This in turn has motivated development of metrics intended to measure the factual consistency of generated summaries against sources. But are these approaches measuring what they purport to? Or are they mostly exploiting artifacts?

Process reward model (PRM) has been proven effective in test-time scaling of LLM on challenging reasoning tasks. However, the reward hacking induced by PRM hinders its successful applications in reinforcement fine-tuning. We find the primary cause of reward hacking induced by PRM is that: the canonical summation-form credit assignment in reinforcement learning (RL), i.e. cumulative gamma-decayed future rewards, causes the LLM to hack steps with high rewards. Therefore, to unleashing the power of PRM in training-time, we propose PURE: Process sUpervised Reinforcement lEarning. The core of PURE is the min-form credit assignment that defines the value function as the minimum future rewards.

This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to ground-truth information. While this setting appears elusive, we find that common practices in Test-Time Scaling (TTS), such as majority voting, yield surprisingly effective rewards suitable for driving RL training. In this work, we introduce Test-Time Reinforcement Learning (TTRL), a novel method for training LLMs using RL on unlabeled data. TTRL enables self-evolution of LLMs by utilizing the priors in the pre-trained models. Our experiments demonstrate that TTRL consistently improves performance across a variety of tasks and models. Notably, TTRL boosts the pass@1 performance of Qwen-2.5-Math-7B by approximately 211% on the AIME 2024 with only unlabeled test data. Furthermore, although TTRL is only supervised by the Maj@N metric, TTRL has demonstrated performance to consistently surpass the upper limit of the initial model, and approach the performance of models trained directly on test data with ground-truth labels. Our experimental findings validate the general effectiveness of TTRL across various tasks and highlight TTRL's potential for broader tasks and domains.

The recent development of zero-shot reinforcement learning (RL) has opened a new avenue for learning pre-trained generalist policies that can adapt to arbitrary new tasks in a zero-shot manner. While the popular Forward-Backward representations (FB) and related methods have shown promise in zero-shot RL, we empirically found that their modeling lacks expressivity and that extrapolation errors caused by out-of-distribution (OOD) actions during offline learning sometimes lead to biased representations, ultimately resulting in suboptimal performance. To address these issues, we propose Behavior-REgularizEd Zero-shot RL with Expressivity enhancement (BREEZE), an upgraded FB-based framework that simultaneously enhances learning stability, policy extraction capability, and representation learning quality. BREEZE introduces behavioral regularization in zero-shot RL policy learning, transforming policy optimization into a stable in-sample learning paradigm.

Math reasoning has been one crucial ability of large language models (LLMs), where significant advancements have been achieved in recent years. However, most efforts focus on LLMs by curating high-quality annotation data and intricate training (or inference) paradigms, while the math reasoning performance of multi-modal LLMs (MLLMs) remains lagging behind. Since the MLLM typically consists of an LLM and vision block, we wonder: \textit{Can MLLMs directly absorb math reasoning abilities from off-the-shelf math LLMs without tuning?} Recent model-merging approaches may offer insights into this question. However, they overlook the alignment between the MLLM and LLM, where we find that there is a large gap between their parameter spaces, resulting in lower performance. Our empirical evidence reveals two key factors behind this issue: the identification of crucial reasoning-associated layers in the model and the mitigation of the gaps in parameter space. Based on the empirical insights, we propose \textbf{IP-Merging} that first \textbf{I}dentifies the reasoning-associated parameters in both MLLM and Math LLM, then \textbf{P}rojects them into the subspace of MLLM aiming to maintain the alignment, finally merges parameters in this subspace. IP-Merging is a tuning-free approach since parameters are directly adjusted. Extensive experiments demonstrate that our IP-Merging method can enhance the math reasoning ability of MLLMs directly from Math LLMs without compromising their other capabilities.

Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively regenerate only the intended editing areas. This results in (1) unnecessary computational costs and (2) a bias toward reconstructing non-editing regions, which compromises the quality of the intended edits. To resolve these limitations, we propose to formulate image editing as $\textbf{N}$ext $\textbf{E}$diting-token $\textbf{P}$rediction (NEP) based on autoregressive image generation, where only regions that need to be edited are regenerated, thus avoiding unintended modification to the non-editing areas. To enable any-region editing, we propose to pre-train an any-order autoregressive text-to-image (T2I) model. Once trained, it is capable of zero-shot image editing and can be easily adapted to NEP for image editing, which achieves a new state-of-the-art on widely used image editing benchmarks. Moreover, our model naturally supports test-time scaling (TTS) through iteratively refining its generation in a zero-shot manner.

However, a prevalent issue is ``superficial self-reflection'', where models fail to robustly verify their own outputs. We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this. RISE explicitly and simultaneously trains an LLM to improve both its problem-solving and self-verification abilities within a single, integrated RL process. The core mechanism involves leveraging verifiable rewards from an outcome verifier to provide on-the-fly feedback for both solution generation and self-verification tasks. In each iteration, the model generates solutions, then critiques its own on-policy generated solutions, with both trajectories contributing to the policy update. Extensive experiments on diverse mathematical reasoning benchmarks show that RISE consistently improves model's problem-solving accuracy while concurrently fostering strong self-verification skills. Our analyses highlight the advantages of online verification and the benefits of increased verification compute.

Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficiently addressed by techniques developed for dense models. In this work, the MoE-specific safety risk of positional vulnerability--that safety-aligned behaviors rely on specific expert modules--is formalized and systematically analyzed. An analytical framework, SAFEx, is presented to robustly identify, characterize, and validate safety-critical experts via a stability-based expert selection procedure, and to decompose them into two functional groups: the Harmful Content Detection Group (HCDG), which specializes in identifying and recognizing harmful content within user inputs, and the Harmful Response Control Group (HRCG), which specializes in controlling and enforcing model behaviors to generate appropriate safety responses. Expert-level interventions are conducted to probe causality and to test mitigation. Targeted masking of SAFEx-selected experts reveals that safety behavior is highly concentrated. On Qwen3-30B-A3B, configured with 48 MoE-FFN layers and 128 experts per layer under top-8 routing (48 128=6,144 experts in total), disabling 12 selected experts reduces the refusal rate by 22%. In addition, lightweight adaptation is performed using LoRA under three configurations--the HRCG, the union of HCDG and HRCG, and all experts--and the resulting updates are composed through negative weight merging targeted at the HRCG, leading to improved refusal under adversarial prompts without full-model retraining. These results establish positional vulnerability as a distinct MoE-specific safety challenge and provide a practical, compute-efficient pathway for expert-level safety interventions within routed architectures.

Extracting optical flow from videos remains a core computer vision problem. Motivated by the recent success of large general-purpose models, we ask whether frozen self-supervised video models trained only to predict future frames can be prompted, without fine-tuning, to output flow. Prior attempts to read out depth or illumination from video generators required fine-tuning; that strategy is ill-suited for flow, where labeled data is scarce and synthetic datasets suffer from a sim-to-real gap. Inspired by the Counterfactual World Model (CWM) paradigm, which can obtain point-wise correspondences by injecting a small tracer perturbation into a next-frame predictor and tracking its propagation, we extend this idea to generative video models for zero-shot flow extraction. We explore several popular architectures and find that successful zero-shot flow extraction in this manner is aided by three model properties: (1) distributional prediction of future frames (avoiding blurry or noisy outputs); (2) factorized latents that treat each spatio-temporal patch independently; and (3) random-access decoding that can condition on any subset of future pixels. These properties are uniquely present in the recently introduced Local Random Access Sequence (LRAS) architecture. Building on LRAS, we propose KL-tracing: a novel test-time inference procedure that injects a localized perturbation into the first frame, rolls out the model one step, and computes the Kullback-Leibler divergence between perturbed and unperturbed predictive distributions. Without any flow-specific fine-tuning, our method is competitive with state-of-the-art, task-specific models on the real-world TAP-Vid DAVIS benchmark and the synthetic TAP-Vid Kubric. Our results show that counterfactual prompting of controllable generative video models is an effective alternative to supervised or photometric-loss methods for high-quality flow.