Mathematical reasoning has long been a key benchmark for evaluating large language models. Although substantial progress has been made on math word problems, the need for reasoning over tabular data in real-world applications has been overlooked. For instance, applications such as business intelligence demand not only multi-step numerical reasoning with tables but also robustness to incomplete or inconsistent information. However, comprehensive evaluation in this area is severely limited, constrained by the reliance on manually collected tables that are difficult to scale and the lack of coverage for potential traps encountered in real-world scenarios. To address this problem, we propose AutoT2T, a neuro-symbolic framework that controllably transforms math word problems into scalable and verified tabular reasoning tasks. Building on this pipeline, we develop TabularMath, a benchmark comprising four subsets that include both text-based and image-based tables, covering table complexity, table quality, and table representation dimensions. Our study reveals three key observations: (1) Table complexity and reasoning difficulty impact reasoning performance jointly; (2) Low-quality tables pose severe risks to reliable reasoning in current LLMs; (3) Different table modalities show similar trends, with text-based tables typically being easier for models to reason over. In-depth analyses are conducted for each observation to guide future research.

Reasoning-enhanced large language models rely on intermediate reasoning signals to solve complex, multi-step tasks, making reasoning behavior a valuable form of intellectual property. Meanwhile, knowledge distillation enables an adversary to replicate this behavior in a realistic black-box setting by repeatedly querying a deployed model on a target domain and training a local student to imitate its outputs, including reasoning traces. Existing LLM watermarks primarily operate on surface text and decoding-time token biases, and thus fail to provide reliable attribution of reasoning behavior once it is transferred through knowledge distillation. ReasMark entangles the watermark with the target-domain input distribution by selecting watermark tokens from high-frequency prompts, so distillation queries naturally activate it. It then embeds the watermark by score-conditioned losses that create a detectable reasoning-length gap for black-box verification. Comprehensive experiments across multiple LLMs, datasets, and distillation settings demonstrate that ReasMark consistently outperforms existing baselines while preserving task utility.

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly refuse benign requests. A key goal of safe alignment is therefore to improve safety while simultaneously minimizing false refusals. In this work, we introduce Energy Landscape Steering (ELS), a novel, fine-tuning free framework designed to resolve this challenge through dynamic, inference-time intervention. We trained a lightweight, external Energy-Based Model (EBM) to assign high energy to undesirable (false refusal or jailbreak) states and low energy to desirable (helpful response or safe reject) ones. During inference, the EBM maps the LLM’s internal activations to an energy landscape, and we use the gradient of the energy function to steer the hidden states toward low-energy regions in real time. This dynamically guides the model toward desirable behavior without modifying its parameters. By decoupling behavioral control from the model’s core knowledge, ELS provides a flexible and computationally efficient solution. Extensive experiments across diverse models demonstrate its effectiveness: raising compliance on the ORB-H benchmark from 57.3% to 82.6% while maintaining the baseline safety performance. Our work establishes a promising paradigm for building LLMs that simultaneously achieve high safety and low false refusal rates.

The increasing prevalence of embedded systems has necessitated manufacturers to migrate product code, transferring existing products to new embedded operating systems (OSes) for getting better compatibility and performance. Since manufacturers’ product code predominantly employs the Thing Specification Language (TSL) paradigm for cloud connectivity, migrated code consequently adheres to the same TSL standard. However, embedded code migration under the TSL paradigm proves more complex than conventional code migration. Neither outline-based code generation nor common code translation techniques can adequately address this challenge, despite their prevalence in existing systems. There exists a growing demand for a algorithm tailored to TSL paradigm embedded code migration. In response to this demand, we have developed IoTMigrator that employs a multi-agent pipeline to handle the issue. The key insight of our algorithm is the TSL enhancer, specifically designed for the characteristics of the TSL paradigm, which serves as a crucial component in the agent pipeline.To demonstrate the superiority of our algorithm, we have established our own benchmark, which includes six tasks across two OSes, RIOT and Zephyr. We adopted two key metrics: compilation pass rate and task completeness score. The experiment results show that our algorithm outperforms the baseline by an average of at least 50.5% for pass rate and 13.0% for completeness across all tasks in RIOT, and at least 83.4% for pass rate and 18.4% for completeness in Zephyr. This work will be open-sourced in the future.

Large language models are reshaping internet services. Serving these models is often costly, as it requires multiple high-end GPUs. Consumer-grade GPUs offer cheaper computational power, providing an opportunity for more cost-efficient LLM serving.Prior efforts have explored distributed serving at scale, primarily focusing on model deployment strategies. However, communication efficiency has emerged as a challenge due to the imbalance in data transfer volumes between the two phases of inference: prefill and decode. Prefill requests can involve transmitting up to 1000 times more data than decode requests, leading to decode requests being delayed. Consequently, servers are underutilized while waiting for decode requests. In this paper, we present MoLink, an efficient distributed LLM serving system. It splits the prolonged transmission volume of prefill requests into smaller chunks and carefully scheduling their transmission. It consists of two parts: (i) a transmission scheduling algorithm that fairly determines whether to transmit prefill or decode requests, and (ii) a chunking determination algorithm that determines the transmit volume for prefill requests just-in-time. Our evaluation demonstrates that MoLink reduces TTFT, TPOT, and latency compared to the state-of-the-art distributed LLM serving system, with a maximum reduction of up to 46%.

The rapid advancement of large language models (LLMs) in recent years has made it feasible to establish domain-specific LLMs for specialized fields. However, in practical development, acquiring domain-specific knowledge often requires a significant amount of professional expert manpower. Moreover, even when domain-specific data is available, the lack of a unified methodology for benchmark dataset establishment often results in uneven data distribution. This imbalance can lead to an inaccurate assessment of the true model capabilities during the evaluation of domain-specific LLMs. To address these challenges, we introduce **SDBench**, a generic framework for generating evaluation datasets for domain-specific LLMs. This method is also applicable for establishing the LLM instruction datasets. It significantly reduces the reliance on expert manpower while ensuring that the collected data is uniformly distributed. To validate the effectiveness of this framework, we also present the **BridgeBench**, a novel benchmark for bridge engineering knowledge, and the **BridgeGPT**, the first LLM specialized in bridge engineering, which can solve bridge engineering tasks.

Hashing is promising for large-scale information retrieval tasks thanks to the efficiency of distance evaluation between binary codes. Generative hashing is often used to generate hashing codes in an unsupervised way. However, existing generative hashing methods only considered the use of simple priors, like Gaussian and Bernoulli priors, which limits these methods to further improve their performance. In this paper, two mixture-prior generative models are proposed, under the objective to produce high-quality hashing codes for documents. Specifically, a Gaussian mixture prior is first imposed onto the variational auto-encoder (VAE), followed by a separate step to cast the continuous latent representation of VAE into binary code. To avoid the performance loss caused by the separate casting, a model using a Bernoulli mixture prior is further developed, in which an end-to-end training is admitted by resorting to the straight-through (ST) discrete gradient estimator. Experimental results on several benchmark datasets demonstrate that the proposed methods, especially the one using Bernoulli mixture priors, consistently outperform existing ones by a substantial margin.