Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning capability of Large Language Models (LLMs). Current RLVR trains LLMs on all generated tokens, rather than exploring which tokens actually contribute to reasoning. We propose AIPO(Adaptive–Information Policy Optimization), which focuses updates on those decisive tokens discovered on the fly. AIPO estimates each hidden state’s mutual information to score tokens. Policy gradients are then computed only on these critical tokens, using an advantage that blends information gain and verifiable correctness. To improve the efficiency of mutual-information estimation, AIPO adopts a Random–Fourier approximation of the Hilbert–Schmidt Independence Criterion. Across five math and science benchmarks, AIPO yields up to +20% accuracy over strong RLVR baselines while updating merely 10% of tokens, demonstrating superior efficiency and effectiveness. Our findings highlight the importance of information–driven token selection for efficient and effective reinforcement learning of LLM reasoning.

Logical reasoning is a key capability of large language models, yet current benchmarks focus almost entirely on tasks that just check basic logical consistency and overlook the reflective reasoning required for paradox detection and resolution.To fill the gap, we present ParaSuite, the first pipeline dedicated to paradox research that automates data synthesis, evaluation, and training.We introduce PARADOX, a synthetic, high-quality data spanning two difficulty tiers and three academic domains, accompanied by specialized evaluation metrics and solving algorithms.We propose ParadoxBreaker-7B, trained with Mutual-Information Guided Fine-Tuning and reinforcement learning step verify paradox reward(PAPO).Experiments demonstrate significant improvements in both paradoxical and general STEM reasoning.

With the widespread adoption of large vision-language models, the capacity for color vision in these models is crucial. However, the color vision abilities of large visual-language models have not yet been thoroughly explored. To address this gap, we define a color vision testing task for large vision-language models and construct a dataset that covers multiple categories of test questions and tasks of varying difficulty levels. Furthermore, we analyze the types of errors made by large vision-language models and propose a chain-of-thought prompting strategy to enhance their performance in color vision tests.

Emotion and Intent Joint Understanding in Multi-modal Conversation is a challenging task in the field of affective computing, aiming to decode the semantic information manifested in the multimodal conversational while simultaneously inferring the emotions and intents of the utterance. To address this challenge, we propose the Text-guided Multimodal Emotion-Intent Joint Recognition method. By leveraging the text modality to guide the fusion process, it effectively reduces the noise introduced by other modalities. To strengthen the text modality’s guiding role, we use large language models (LLMs) for multi-turn targeted data augmentation and oversampling strategies to address data imbalance. Our approach achieved first place in Track 1 (English) of the ICASSP 2025 MEIJU Challenge, demonstrating its effectiveness in practical applications.

We propose a fast intersection-free remeshing of triangular meshes that robustly and efficiently generates high-quality non-intersecting meshes. Conducting intersection checks on all local operations during remeshing to prevent intersections represents the principal efficiency bottleneck. Our method is based on a key observation: intersections primarily occur in structurally complex regions. Accordingly, we develop an adaptive method to identify these key regions and perform intersection checks only for local operations within these regions during remeshing, significantly improving the algorithmic efficiency. Our method is an order of magnitude faster than traditional approaches that perform intersection checks on all local operations. Furthermore, we introduce a flip-aware extension mechanism that effectively avoids triangle flipping by constraining the optimization space of local operations, thereby avoiding the formation of irregular sharp edges. We also employ an adaptive iterative size field to eliminate banding phenomenon and propose a quasi-geometric size field adjustment method to quickly achieve smooth size transitions, thereby improving mesh quality. Compared to state-of-the-art methods, our method consistently and quickly generates higher quality non-intersecting meshes. In addition, we have validated the robustness and efficiency of our method, using all 5,469 non-intersecting valid models from the Thingi10K dataset.

A novel ΔΣ time-to-digital converter (TDC) with a time mode accumulator and a multi-bit quantizer is proposed in this work. Measurement time is reduced when compared with single-bit ΔΣ TDCs. A time difference adder consisting of gated delay-line based time-registers is used to serve as the time accumulator. A dynamic element matching algorithm is implemented to mitigate the performance loss degraded by the non-linearity of the multi-bit quantizer. The TDC is designed and simulated using a 65nm CMOS process and operates at a 100MHz sampling rate. For a 1.25MHz bandwidth, 108fsrmsintegrated noise or 2.4ps equivalent resolution is achieved. The power consumption is only 0.45 mW and the figure of merit (FoM) is calculated to be 154fJ/step.

This paper presents a new test access mechanism (TAM) architecture and optimization method based on an improved flexible-width test bus. The method is first to set up the test time lower bound that is not depends on TAM architecture, then to construct a bus assignment that makes test time up to the lower bound. We present experimental results on our improved flexible-width test buses for four benchmark SOCs. Experiment results in a significant reduction of the test time, and is better than the proposed traditional methods in test time.