Entropy mechanism emerges as a key organizing principle for understanding and improving Large Reasoning Models (LRMs). This survey examines how entropy shapes both their training and inference behavior. On the training side, we take a mathematical perspective: casting existing RL-based reasoning algorithms into a unified objective and using this formulation to derive an entropy-centric decomposition of methods, clarifying how different approaches adjust exploration–exploitation "knobs". On the inference side, based on the characteristic of LRM that trading increased inference tokens yields better performance, we summarize methods that leverage entropy to enhance inference performance or reduce uncertainty. Finally, we discuss open challenges and future directions of entropy-driven research for LRMs. Our repository is available on https://anonymous.4open.science/r/Awesome_LRM_with_Entropy-0503.

Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically degrades this text’s reasoning capability, undermining multimodal performance. To address this issue, we propose a training-free framework to mitigate this degradation. Through layer-wise vision token masking, we reveal a common three-stage pattern in multimodal large language models: early-modal separation, mid-modal alignment, and late-modal degradation. By analyzing the behavior of MLLMs at different stages, we propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs. Experimental results based on five MLLMs on nine benchmarks demonstrate the effectiveness of our method. Attention-based analysis further reveals that merging shifts attention from diffuse, scattered patterns to focused localization on task-relevant visual regions.Our repository is on https://github.com/wzj1718/PlaM .

The rapid development of LLMs incurs prohibitive memory footprints and intensive computational demands. Quantization-Aware Training (QAT) techniques have emerged as a promising solution to address these challenges by explicitly simulating quantization effects during model training, yielding low-bit models that achieve accuracy comparable to their full-precision counterparts. In this work, we provide a target-centric survey of QAT, aimed at clarifying both its theoretical foundations and its evolving implementation landscape. We systematically review existing QAT methods through a target-centric taxonomy and synthesize cross-target differences in error characteristics, numerical formats, and strategy transferability. We further summarize QAT evaluation paradigms and discuss challenges in optimization and deployment, outlining potential directions for future research.

Audio-language models (ALMs) often follow text that conflicts with audio, even when the audio evidence is clear. This behavior leaves an important question unresolved: is the audio-supported answer unavailable, or is it represented but overridden by the conflicting text? We test this question with a same-audio counterfactual that keeps the audio fixed, removes only the conflicting text, and measures the resulting shift in model preference. Across five ALMs and four conflict tasks, 64.1% of conflict samples exhibit a sign flip: the same-audio branch prefers the audio-supported answer, whereas the joint branch prefers the text-supported answer. This pattern suggests that the relevant audio evidence is encoded but loses during arbitration. Activation patching further localizes the reversal to answer-position computation, and patching effects closely track output candidate-score differences (Spearman ρ=0.93). Based on this diagnostic, we propose Gated Audio Counterfactual Logit Correction (GACL), a training-free decoding rule that interpolates between joint and same-audio scores. Under a strict 5 pp faithfulness-drop budget, GACL improves nAUC by 17.8 points over the best contrastive baseline and transfers without retuning to vision-text arbitration (up to +40.5 pp).

Parameter-Efficient Fine-Tuning (PEFT) has become a popular alternative to Full-Parameter Fine-Tuning (FFT), achieving similar performance on many benchmarks with far lower computational and memory costs. Yet, its effectiveness on complex tasks such as reasoning and instruction-following remains unclear. In this work, we provide a theoretical and empirical comparison of PEFT and FFT in terms of representational capacity and robustness. We show that PEFT’s solution space is a strict subset of FFT’s and derive upper bounds revealing how its restricted parameterization limits expressiveness and increases vulnerability to perturbations. Experiments on 20 datasets and 11 adversarial test sets support these findings, indicating that while PEFT performs well on standard tasks, its weaknesses on complex and adversarial settings call for new directions beyond current PEFT paradigms.The source code is in the anonymous GitHub repository[https://anonymous.4open.science/r/PEFTEval-E2AC ].

Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model. However, existing methods struggle to maintain performance gains as the number of merged models increases. In this paper, we investigate the key obstacles that limit the scalability of model merging. We prove that the limited effective parameter space imposes a strict constraint on the number of models that can be successfully merged. Through Gaussian Width analysis, we show that marginal benefits diminish according to a strictly concave function as more models are merged. Using Approximate Kinematics Theory, we further prove the existence of a unique optimal threshold beyond which additional models yield negligible improvements. To address this limitation, we propose a straightforward Reparameterized Heavy-Tailed method to extend the merged model’s coverage and enhance performance. Empirical results on 19 benchmarks, including both knowledge-intensive and general-purpose tasks, validate our theoretical analysis. We believe that these results spark further research beyond the current scope of model merging.