Large Language Models (LLMs) with chains-of-thought have demonstrated strong performance on an increasing range of tasks, particularly those involving complex logical reasoning. However, excessively long chains can lead to overthinking, causing computational waste and slower responses. This raises a question: can LLMs dynamically adjust the length of their reasoning processes based on task complexity? To address this, we propose the Think in Blocks framework, which enables adaptive reasoning-from zero to deep reasoning-by partitioning the reasoning process into a tunable number of blocks. Our main contributions are: (1) Establishing an explicit block-structured paradigm in which the model first predicts an integer reasoning budget-the number of blocks-and then partitions its reasoning accordingly; (2) Training an adaptive model through a three-stage pipeline-Supervised Fine-Tuning, reward-guided Direct Preference Optimization, and Reinforcement Learning-that adjusts its reasoning depth to problem difficulty; (3) Exploiting the explicit block count to dynamically control reasoning depth at inference time, allowing flexible adjustment of chain-of-thought length during deployment.

We introduce Dream 7B, the most powerful open diffusion large language model to date. Unlike autoregressive (AR) models that generate tokens sequentially, Dream 7B employs discrete diffusion modeling to refine sequences in parallel through iterative denoising. Our model consistently outperforms existing diffusion language models on general, mathematical, and coding tasks. Dream 7B demonstrates superior planning abilities and inference flexibility, including arbitrary-order generation, infilling capabilities, and tunable quality-speed trade-offs. These results are achieved through simple yet effective training techniques, including AR-based LLM initialization and context-adaptive token-level noise rescheduling. We release both Dream-Base and Dream-Instruct to facilitate further research in diffusion-based language modeling.

While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally, machine unlearning has emerged as a representative paradigm to ensure model safety. Existing approaches employ various training techniques, such as gradient ascent and negative preference optimization, in attempts to eliminate the influence of undesired data on target models. However, these methods merely suppress the activation of undesired data through parametric training without completely eradicating its informational traces within the model. This fundamental limitation makes it difficult to achieve effective continuous unlearning, rendering these methods vulnerable to relearning attacks. To overcome these challenges, we propose a Metamorphosis Representation Projection (MRP) approach that pioneers the application of irreversible projection properties to machine unlearning. By implementing projective transformations in the hidden state space of specific network layers, our method effectively eliminates harmful information while preserving useful knowledge. Experimental results demonstrate that our approach enables effective continuous unlearning and successfully defends against relearning attacks, achieving state-of-the-art performance in unlearning effectiveness while preserving natural performance. Our code is available in https://github.com/ChengcanWu/MRP.

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency. Knowledge distillation (KD), a promising model compression and acceleration technique, addresses these limitations by transferring knowledge from large teacher models to compact student models, enabling efficient inference while preserving most of the teacher models' capabilities. While this technique has shown remarkable success in natural language processing and computer vision domains, its potential for code understanding tasks remains largely underexplored. In this paper, we systematically investigate the effectiveness and usage of KD in code understanding tasks. Our study encompasses two popular types of KD methods, i.e., logit-based and feature-based KD methods, experimenting across eight student models and two teacher PLMs from different domains on three downstream tasks. The experimental results indicate that KD consistently offers notable performance boosts across student models with different sizes compared with standard fine-tuning. Notably, code-specific PLM demonstrates better effectiveness as the teacher model. Among all KD methods, the latest feature-based KD methods exhibit superior performance, enabling student models to retain up to 98% teacher performance with merely 5% parameters. Regarding student architecture, our experiments reveal that similarity with teacher architecture does not necessarily lead to better performance. We further discuss the efficiency and behaviors in the KD process and inference, summarize the implications of findings, and identify promising future directions.

Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. While recent studies have explored the use of deep learning for preliminary surgical wound screening, progress has been hindered by concerns over data privacy and the high costs associated with expert annotation. Currently, no publicly available dataset or benchmark encompasses various types of surgical wounds, resulting in the absence of an open-source Surgical-Wound screening tool. To address this gap: (1) we present SurgWound, the first open-source dataset featuring a diverse array of surgical wound types. It contains 697 surgical wound images annotated by 3 professional surgeons with eight fine-grained clinical attributes. (2) Based on SurgWound, we introduce the first benchmark for surgical wound diagnosis, which includes visual question answering (VQA) and report generation tasks to comprehensively evaluate model performance. (3) Furthermore, we propose a three-stage learning framework, WoundQwen, for surgical wound diagnosis. In the first stage, we employ five independent MLLMs to accurately predict specific surgical wound characteristics. In the second stage, these predictions serve as additional knowledge inputs to two MLLMs responsible for diagnosing outcomes, which assess infection risk and guide subsequent interventions. In the third stage, we train a MLLM that integrates the diagnostic results from the previous two stages to produce a comprehensive report. This three-stage framework can analyze detailed surgical wound characteristics and provide subsequent instructions to patients based on surgical images, paving the way for personalized wound care, timely intervention, and improved patient outcomes.

Timely detection of hardware vulnerabilities during the early design stage is critical for reducing remediation costs. Existing early detection techniques often require specialized security expertise, limiting their usability. Recent efforts have explored the use of large language models (LLMs) for Verilog vulnerability detection. However, LLMs struggle to capture the structure in Verilog code, resulting in inconsistent detection results. To this end, we propose VerilogLAVD, the first LLM-aided graph traversal rule generation approach for Verilog vulnerability detection. Our approach introduces the Verilog Property Graph (VeriPG), a unified representation of Verilog code. It combines syntactic features extracted from the abstract syntax tree (AST) with semantic information derived from control flow and data dependency graphs. We leverage LLMs to generate VeriPG-based detection rules from Common Weakness Enumeration (CWE) descriptions. These rules guide the rule executor that traversal VeriPG for potential vulnerabilities. To evaluate VerilogLAVD, we build a dataset collected from open-source repositories and synthesized data. In our empirical evaluation on 77 Verilog designs encompassing 12 CWE types, VerilogLAVD achieves an F1-score of 0.54. Compared to the LLM-only and LLM with external knowledge baselines, VerilogLAVD improves F1-score by 0.31 and 0.27, respectively.

Finite State Machines (FSMs) play a critical role in implementing control logic for Systems-on-Chip (SoC). Traditionally, FSMs are implemented by hardware engineers through Verilog coding, which is often tedious and time-consuming. Recently, with the remarkable progress of Large Language Models (LLMs) in code generation, LLMs have been increasingly explored for automating Verilog code generation. However, LLM-generated Verilog code often suffers from security vulnerabilities, which is particularly concerning for security-sensitive FSM implementations. To address this issue, we propose SecFSM, a novel method that leverages a security-oriented knowledge graph to guide LLMs in generating more secure Verilog code. Specifically, we first construct a FSM Security Knowledge Graph (FSKG) as an external aid to LLMs. Subsequently, we analyze users' requirements to identify vulnerabilities and get a list of vulnerabilities in the requirements. Then, we retrieve knowledge from FSKG based on the vulnerabilities list. Finally, we construct security prompts based on the security knowledge for Verilog code generation. To evaluate SecFSM, we build a dedicated dataset collected from academic datasets, artificial datasets, papers, and industrial cases. Extensive experiments demonstrate that SecFSM outperforms state-of-the-art baselines. In particular, on a benchmark of 25 security test cases evaluated by DeepSeek-R1, SecFSM achieves an outstanding pass rate of 21/25.

Next-generation mobile networks must reconcile the often-conflicting goals of multiple service owners. However, today's network slice controllers remain rigid, policy-bound, and unaware of the business context. We introduce Agoran Service and Resource Broker (SRB), an agentic marketplace that brings stakeholders directly into the operational loop. Inspired by the ancient Greek agora, Agoran distributes authority across three autonomous AI branches: a Legislative branch that answers compliance queries using retrieval-augmented Large Language Models (LLMs); an Executive branch that maintains real-time situational awareness through a watcher-updated vector database; and a Judicial branch that evaluates each agent message with a rule-based Trust Score, while arbitrating LLMs detect malicious behavior and apply real-time incentives to restore trust. Stakeholder-side Negotiation Agents and the SRB-side Mediator Agent negotiate feasible, Pareto-optimal offers produced by a multi-objective optimizer, reaching a consensus intent in a single round, which is then deployed to Open and AI RAN controllers. Deployed on a private 5G testbed and evaluated with realistic traces of vehicle mobility, Agoran achieved significant gains: (i) a 37% increase in throughput of eMBB slices, (ii) a 73% reduction in latency of URLLC slices, and concurrently (iii) an end-to-end 8.3% saving in PRB usage compared to a static baseline. An 1B-parameter Llama model, fine-tuned for five minutes on 100 GPT-4 dialogues, recovers approximately 80% of GPT-4.1's decision quality, while operating within 6 GiB of memory and converging in only 1.3 seconds. These results establish Agoran as a concrete, standards-aligned path toward ultra-flexible, stakeholder-centric 6G networks. A live demo is presented https://www.youtube.com/watch?v=h7vEyMu2f5w\&ab_channel=BubbleRAN.

Bail decisions are among the most frequently adjudicated matters in Indian courts, yet they remain plagued by subjectivity, delays, and inconsistencies. With over 75% of India's prison population comprising undertrial prisoners, many from socioeconomically disadvantaged backgrounds, the lack of timely and fair bail adjudication exacerbates human rights concerns and contributes to systemic judicial backlog. In this paper, we present the Indian Bail Prediction System (IBPS), an AI-powered framework designed to assist in bail decision-making by predicting outcomes and generating legally sound rationales based solely on factual case attributes and statutory provisions. We curate and release a large-scale dataset of 150,430 High Court bail judgments, enriched with structured annotations such as age, health, criminal history, crime category, custody duration, statutes, and judicial reasoning. We fine-tune a large language model using parameter-efficient techniques and evaluate its performance across multiple configurations, with and without statutory context, and with RAG. Our results demonstrate that models fine-tuned with statutory knowledge significantly outperform baselines, achieving strong accuracy and explanation quality, and generalize well to a test set independently annotated by legal experts. IBPS offers a transparent, scalable, and reproducible solution to support data-driven legal assistance, reduce bail delays, and promote procedural fairness in the Indian judicial system.

We study evaluation of AI systems without ground truth by exploiting a link between strategic gaming and information loss. We analyze which information-theoretic mechanisms resist adversarial manipulation, extending finite-sample bounds to show that bounded f-divergences (e.g., total variation distance) maintain polynomial guarantees under attacks while unbounded measures (e.g., KL divergence) degrade exponentially. To implement these mechanisms, we model the overseer as an agent and characterize incentive-compatible scoring rules as f-mutual information objectives. Under adversarial attacks, TVD-MI maintains effectiveness (area under curve 0.70-0.77) while traditional judge queries are near change (AUC $\approx$ 0.50), demonstrating that querying the same LLM for information relationships rather than quality judgments provides both theoretical and practical robustness. The mechanisms decompose pairwise evaluations into reliable item-level quality scores without ground truth, addressing a key limitation of traditional peer prediction. We release preregistration and code.