Language models are often said to face a symbol grounding problem. While some have argued the problem can be solved without resort to other modalities, many have speculated that grounded learning is more efficient. We explore this question in Othello, a simplified, rule-based world that offers a controlled and interpretable testbed for studying world understanding. Building on prior work, we introduce VISOTHELLO, a multi-modal model trained jointly on move sequences and board images. Using the Othello rule understanding task, we examine whether multi-modal learning provides advantages over text-only approaches. We further evaluate robustness under semantically irrelevant perturbations and analyze the consistency of cross-modal alignment. Our results suggest that multi-modal training not only improves performance and robustness but also promotes convergence toward shared internal representations across different model architectures.

Large Language Models (LLMs) are commonly finetuned for a variety of use cases and domains. A common approach is to leverage Low-Rank Adaptation (LoRA) -- known to provide strong performance at low resource costs. In this study, we demonstrate that LoRA actually opens the door to short-cut vulnerabilities -- and the more resource efficient is the LoRA setup, the more vulnerable will be the finetuned model to aggressive attacks. To measure that vulnerability, we introduce Seamless Spurious Token Injection (SSTI), where we find that LoRA exclusively focuses on even just a single token that is spuriously correlated with downstream labels. In short, injection of that spurious token during finetuning ensure that the model's prediction at test-time can be manipulated on-demand. We conducted experiments across model families and datasets to evaluate the impact of SSTI during LoRA finetuning while providing possible mitigations. Our experiments conclude that none of the existing checkers and preprocessors can sanitize a dataset raising new concerns for data quality and AI safety.

Inference-time steering aims to alter a large language model's (LLM's) responses without changing its parameters, but a central challenge is identifying the internal modules that most strongly govern the target behavior. Existing approaches often rely on simplistic cues or ad hoc heuristics, leading to suboptimal or unintended effects. We introduce REAL, a framework for identifying behavior-relevant modules (attention heads or layers) in Transformer models. For each module, REAL trains a vector-quantized autoencoder (VQ-AE) on its hidden activations and uses a shared, learnable codebook to partition the latent space into behavior-relevant and behavior-irrelevant subspaces. REAL quantifies a module's behavioral relevance by how well its VQ-AE encodings discriminate behavior-aligned from behavior-violating responses via a binary classification metric; this score guides both module selection and steering strength. We evaluate REAL across eight LLMs from the Llama and Qwen families and nine datasets spanning truthfulness enhancement, open-domain QA under knowledge conflicts, and general alignment tasks. REAL enables more effective inference-time interventions, achieving an average relative improvement of 20% (up to 81.5%) over the ITI method on truthfulness steering. In addition, the modules selected by REAL exhibit strong zero-shot generalization in cross-domain truthfulness-steering scenarios.

With advancements in large audio-language models (LALMs), which enhance large language models (LLMs) with auditory capabilities, these models are expected to demonstrate universal proficiency across various auditory tasks. While numerous benchmarks have emerged to assess LALMs' performance, they remain fragmented and lack a structured taxonomy. To bridge this gap, we conduct a comprehensive survey and propose a systematic taxonomy for LALM evaluations, categorizing them into four dimensions based on their objectives: (1) General Auditory Awareness and Processing, (2) Knowledge and Reasoning, (3) Dialogue-oriented Ability, and (4) Fairness, Safety, and Trustworthiness. We provide detailed overviews within each category and highlight challenges in this field, offering insights into promising future directions. To the best of our knowledge, this is the first survey specifically focused on the evaluations of LALMs, providing clear guidelines for the community. We will release the collection of the surveyed papers and actively maintain it to support ongoing advancements in the field.

Fashion image generation has so far focused on narrow tasks such as virtual try-on, where garments appear in clean studio environments. In contrast, editorial fashion presents garments through dynamic poses, diverse locations, and carefully crafted visual narratives. We introduce the task of virtual fashion photo-shoot, which seeks to capture this richness by transforming standardized garment images into contextually grounded editorial imagery. To enable this new direction, we construct the first large-scale dataset of garment-lookbook pairs, bridging the gap between e-commerce and fashion media. Because such pairs are not readily available, we design an automated retrieval pipeline that aligns garments across domains, combining visual-language reasoning with object-level localization. We construct a dataset with three garment-lookbook pair accuracy levels: high quality (10,000 pairs), medium quality (50,000 pairs), and low quality (300,000 pairs). This dataset offers a foundation for models that move beyond catalog-style generation and toward fashion imagery that reflects creativity, atmosphere, and storytelling.

Large language models (LLMs) are trained on vast amounts of text from the Internet, but do they truly understand the viral content that rapidly spreads online -- commonly known as memes? In this paper, we introduce CHIME, a dataset for CHinese Internet Meme Explanation. The dataset comprises popular phrase-based memes from the Chinese Internet, annotated with detailed information on their meaning, origin, example sentences, types, etc. To evaluate whether LLMs understand these memes, we designed two tasks. In the first task, we assessed the models' ability to explain a given meme, identify its origin, and generate appropriate example sentences. The results show that while LLMs can explain the meanings of some memes, their performance declines significantly for culturally and linguistically nuanced meme types. Additionally, they consistently struggle to provide accurate origins for the memes. In the second task, we created a set of multiple-choice questions (MCQs) requiring LLMs to select the most appropriate meme to fill in a blank within a contextual sentence. While the evaluated models were able to provide correct answers, their performance remains noticeably below human levels. We have made CHIME public and hope it will facilitate future research on computational meme understanding.

Personalizing the outputs of large language models (LLMs) to align with individual user preferences is an active research area. However, previous studies have mainly focused on classification or ranking tasks and have not considered Likert-scale rating prediction, a regression task that requires both language and mathematical reasoning to be solved effectively. This task has significant industrial applications, but the utilization of LLMs remains underexplored, particularly regarding the capabilities of off-the-shelf LLMs. This study investigates the performance of off-the-shelf LLMs on rating prediction, providing different in-context information. Through comprehensive experiments with eight models across three datasets, we demonstrate that user-written reviews significantly improve the rating prediction performance of LLMs. This result is comparable to traditional methods like matrix factorization, highlighting the potential of LLMs as a promising solution for the cold-start problem. We also find that the reviews for concrete items are more effective than general preference descriptions that are not based on any specific item. Furthermore, we discover that prompting LLMs to first generate a hypothetical review enhances the rating prediction performance. Our code is available at https://github.com/ynklab/rating-prediction-with-reviews.

In this appendix, we provide the Proof of Theorem 4.1 which is omitted from the main text due to the space limitation. We should point out that the choice of our potential function works best for a combination of k matroids and null = k knapsacks. When the number of matroid and knapsack constraints is not equal, we can always add redundant constraints so that k is the maximum of the two numbers. For this reason, in the rest of this proof, we assume null = k . Then, we always have φ (S a) φ (S) with γ (S a) < 1. Proof.

In this paper, we introduce a novel technique for constrained submodular maximization, inspired by barrier functions in continuous optimization. This connection not only improves the running time for constrained submodular maximization but also provides the state of the art guarantee. More precisely, for maximizing a monotone submodular function subject to the combination of a k -matchoid and null -knapsack constraints (for null k), we propose a potential function that can be approximately minimized. Once we minimize the potential function up to an ε error, it is guaranteed that we have found a feasible set with a 2(k +1+ ε)-approximation factor which can indeed be further improved to ( k +1+ ε) by an enumeration technique. We extensively evaluate the performance of our proposed algorithm over several real-world applications, including a movie recommendation system, summarization tasks for Y ouTube videos, Twitter feeds and Y elp business locations, and a set cover problem.