Mammogram visual question answering (VQA) integrates image interpretation with clinical reasoning and has potential to support breast cancer screening. We systematically evaluated the GPT-5 family and GPT-4o model on four public mammography datasets (EMBED, InBreast, CMMD, CBIS-DDSM) for BI-RADS assessment, abnormality detection, and malignancy classification tasks. GPT-5 consistently was the best performing model but lagged behind both human experts and domain-specific fine-tuned models. On EMBED, GPT-5 achieved the highest scores among GPT variants in density (56.8%), distortion (52.5%), mass (64.5%), calcification (63.5%), and malignancy (52.8%) classification. On InBreast, it attained 36.9% BI-RADS accuracy, 45.9% abnormality detection, and 35.0% malignancy classification. On CMMD, GPT-5 reached 32.3% abnormality detection and 55.0% malignancy accuracy. On CBIS-DDSM, it achieved 69.3% BI-RADS accuracy, 66.0% abnormality detection, and 58.2% malignancy accuracy. Compared with human expert estimations, GPT-5 exhibited lower sensitivity (63.5%) and specificity (52.3%). While GPT-5 exhibits promising capabilities for screening tasks, its performance remains insufficient for high-stakes clinical imaging applications without targeted domain adaptation and optimization. However, the tremendous improvements in performance from GPT-4o to GPT-5 show a promising trend in the potential for general large language models (LLMs) to assist with mammography VQA tasks.

As Multimodal Large Language Models (MLLMs) gain widespread applicability, it is becoming increasingly desirable to adapt them for diverse user needs. In this paper, we study the adaptation of MLLMs through controlled decoding. T o achieve this, we introduce the first method for reward-guided decoding of MLLMs and demonstrate its application in improving their visual grounding. Our method involves building reward models for visual grounding and using them to guide the MLLM's decoding process. Concretely, we build two separate reward models to independently control the degree of object precision and recall in the model's output. Our approach enables on-the-fly con-trollability of an MLLM's inference process in two ways: first, by giving control over the relative importance of each reward function during decoding, allowing a user to dynamically trade off object precision for recall in image captioning tasks; second, by giving control over the breadth of the search during decoding, allowing the user to control the trade-off between the amount of test-time compute and the degree of visual grounding. W e evaluate our method on standard object hallucination benchmarks, showing that it provides significant controllability over MLLM inference, while consistently outperforming existing hallucination mitigation methods.

Cryptographic algorithms are fundamental to modern security, yet their implementations frequently harbor subtle logic flaws that are hard to detect. We introduce CryptoScope, a novel framework for automated cryptographic vulnerability detection powered by Large Language Models (LLMs). CryptoScope combines Chain-of-Thought (CoT) prompting with Retrieval-Augmented Generation (RAG), guided by a curated cryptographic knowledge base containing over 12,000 entries. We evaluate CryptoScope on LLM-CLVA, a benchmark of 92 cases primarily derived from real-world CVE vulnerabilities, complemented by cryptographic challenges from major Capture The Flag (CTF) competitions and synthetic examples across 11 programming languages. CryptoScope consistently improves performance over strong LLM baselines, boosting DeepSeek-V3 by 11.62%, GPT-4o-mini by 20.28%, and GLM-4-Flash by 28.69%. Additionally, it identifies 9 previously undisclosed flaws in widely used open-source cryptographic projects.

Recent advancements in large language models (LLMs) have greatly improved their capabilities on complex reasoning tasks through Long Chain-of-Thought (CoT). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. To improve the efficiency, current methods often rely on human-defined difficulty priors, which do not align with the LLM's self-awared difficulty, leading to inefficiencies. In this paper, we introduce the Dynamic Reasoning-Boundary Self-Awareness Framework (DR. SAF), which enables models to dynamically assess and adjust their reasoning depth in response to problem complexity. DR. SAF integrates three key components: Boundary Self-Awareness Alignment, Adaptive Reward Management, and a Boundary Preservation Mechanism. These components allow models to optimize their reasoning processes, balancing efficiency and accuracy without compromising performance. Our experimental results demonstrate that DR. SAF achieves a 49.27% reduction in total response tokens with minimal loss in accuracy. The framework also delivers a 6.59x gain in token efficiency and a 5x reduction in training time, making it well-suited to resource-limited settings. During extreme training, DR. SAF can even surpass traditional instruction-based models in token efficiency with more than 16% accuracy improvement.

Cognitive science and neuroscience have long faced the challenge of disentangling representations of language from representations of conceptual meaning. As the same problem arises in today's language models (LMs), we investigate the relationship between LM--brain alignment and two neural metrics: (1) the level of brain activation during processing of sentences, targeting linguistic processing, and (2) a novel measure of meaning consistency across input modalities, which quantifies how consistently a brain region responds to the same concept across paradigms (sentence, word cloud, image) using an fMRI dataset (Pereira et al., 2018). Our experiments show that both language-only and language-vision models predict the signal better in more meaning-consistent areas of the brain, even when these areas are not strongly sensitive to language processing, suggesting that LMs might internally represent cross-modal conceptual meaning.

As large language models (LLMs) become more widely deployed, it is crucial to examine their ethical tendencies. Building on research on fairness and discrimination in AI, we investigate whether LLMs exhibit speciesist bias -- discrimination based on species membership -- and how they value non-human animals. We systematically examine this issue across three paradigms: (1) SpeciesismBench, a 1,003-item benchmark assessing recognition and moral evaluation of speciesist statements; (2) established psychological measures comparing model responses with those of human participants; (3) text-generation tasks probing elaboration on, or resistance to, speciesist rationalizations. In our benchmark, LLMs reliably detected speciesist statements but rarely condemned them, often treating speciesist attitudes as morally acceptable. On psychological measures, results were mixed: LLMs expressed slightly lower explicit speciesism than people, yet in direct trade-offs they more often chose to save one human over multiple animals. A tentative interpretation is that LLMs may weight cognitive capacity rather than species per se: when capacities were equal, they showed no species preference, and when an animal was described as more capable, they tended to prioritize it over a less capable human. In open-ended text generation tasks, LLMs frequently normalized or rationalized harm toward farmed animals while refusing to do so for non-farmed animals. These findings suggest that while LLMs reflect a mixture of progressive and mainstream human views, they nonetheless reproduce entrenched cultural norms around animal exploitation. We argue that expanding AI fairness and alignment frameworks to explicitly include non-human moral patients is essential for reducing these biases and preventing the entrenchment of speciesist attitudes in AI systems and the societies they influence.

Addressing large-scale planning problems has become one of the central challenges in the planning community, deriving from the state-space explosion caused by growing objects and actions. Recently, researchers have explored the effectiveness of leveraging Large Language Models (LLMs) to generate helpful actions and states to prune the search space. However, prior works have largely overlooked integrating LLMs with domain-specific knowledge to ensure valid plans. In this paper, we propose a novel LLM-assisted planner integrated with problem decomposition, which first decomposes large planning problems into multiple simpler sub-tasks. Then we explore two novel paradigms to utilize LLMs, i.e., LLM4Inspire and LLM4Predict, to assist problem decomposition, where LLM4Inspire provides heuristic guidance according to general knowledge and LLM4Predict employs domain-specific knowledge to infer intermediate conditions. We empirically validate the effectiveness of our planner across multiple domains, demonstrating the ability of search space partition when solving large-scale planning problems. The experimental results show that LLMs effectively locate feasible solutions when pruning the search space, where infusing domain-specific knowledge into LLMs, i.e., LLM4Predict, holds particular promise compared with LLM4Inspire, which offers general knowledge within LLMs.

Open-vocabulary Object Goal Navigation requires an embodied agent to reach objects described by free-form language, including categories never seen during training. Existing end-to-end policies overfit small simulator datasets, achieving high success on training scenes but failing to generalize and exhibiting unsafe behaviour (frequent collisions). We introduce OVSegDT, a lightweight transformer policy that tackles these issues with two synergistic components. The first component is the semantic branch, which includes an encoder for the target binary mask and an auxiliary segmentation loss function, grounding the textual goal and providing precise spatial cues. The second component consists of a proposed Entropy-Adaptive Loss Modulation that is a per-sample scheduler that continuously balances imitation and reinforcement signals according to the policy entropy, eliminating brittle manual phase switches. These additions cut the sample complexity of training by 33%, and reduce collision count in two times while keeping inference cost low (130M parameters, RGB-only input). On HM3D-OVON, our model matches the performance on unseen categories to that on seen ones and establishes state-of-the-art results (40.1% SR, 20.9% SPL on val unseen) without depth, odom-etry, or large vision-language models.

In particular, due to their high applicability in textual data, many studies have implemented sentiment analysis using LLMs [2]. LLMs indeed demonstrate remarkable capabilities in understanding textual context; however, the actual'context' is referred to as a relationship between the tokens, which is captured through Transformer [3] and attention mechanisms [4] and most existing approaches limit their analysis to the linguistic context within review texts alone. Regarding real-world marketing applications, the actual context of consumer evaluation contains the factors which extend far beyond the written review, such as past purchasing patterns, prior experiences with the business, comparative evaluations against competitors, and opinions from social media. This gap is particularly relevant in customer relationship management (CRM) [5, 6], where understanding customer sentiment accurately drives business decisions. Marketing research has long established through prospect theory [7] and expectation-disconfirmation theory (EDT) [8] that consumers evaluate experiences relative to these broader reference points. This insight remains largely unexplored in LLM-based sentiment analysis. Furthermore, in practical deployment scenarios, particularly for real-time recommendation systems, two critical challenges emerge. First, computational efficiency is paramount--many businesses cannot deploy large models (70B+ parameters) due to latency and infrastructure constraints. Second, despite having rich contextual data (user histories, business metrics), current methods fail to effectively incorporate this information into LLM-based sentiment analysis.

Anti-sexist speech, i.e., public expressions that challenge or resist gendered abuse and sexism, plays a vital role in shaping democratic debate online. Yet automated content moderation systems, increasingly powered by large language models (LLMs), may struggle to distinguish such resistance from the sexism it opposes. This study examines how five LLMs classify sexist, anti-sexist, and neutral political tweets from the UK, focusing on high-salience trigger events involving female Members of Parliament in the year 2022. Our analysis show that models frequently misclassify anti-sexist speech as harmful, particularly during politically charged events where rhetorical styles of harm and resistance converge. These errors risk silencing those who challenge sexism, with disproportionate consequences for marginalised voices. We argue that moderation design must move beyond binary harmful/not-harmful schemas, integrate human-in-the-loop review during sensitive events, and explicitly include counter-speech in training data. By linking feminist scholarship, event-based analysis, and model evaluation, this work highlights the sociotechnical challenges of safeguarding resistance speech in digital political spaces.