Large language models (LLMs) and Vision language models (VLMs) have been able to perform various forms of reasoning tasks in a wide range of scenarios, but are they truly engaging in task abstraction and rule-based reasoning beyond mere memorization and pattern matching? To answer this question, we propose a novel experimental approach, Misleading Fine-Tuning (MisFT), to examine whether LLMs/VLMs perform abstract reasoning by altering their original understanding of fundamental rules. In particular, by constructing a dataset with math expressions that contradict correct operation principles, we fine-tune the model to learn those contradictory rules and assess its generalization ability on different test domains. Through a series of experiments, we find that current LLMs/VLMs are capable of effectively applying contradictory rules to solve practical math word problems and math expressions represented by images, implying the presence of an internal mechanism that abstracts before reasoning.

Transformer-based LLMs spend most of their compute in large matrix multiplications for attention and feed-forward layers. Recognizing that the Q, K, and V linear projections within the Multi-Head Self-Attention (MHA) module represent a critical computational bottleneck, we strategically focused our efforts on accelerating these operations. We present a tiled matrix multiplication accelerator optimized for such workloads on a Xilinx KV260 on-board FPGA. Key innovations include persistent on-chip storage for one matrix operand, two-level tiling for data reuse, and a systolic-like unrolled compute engine. Implemented via high-level synthesis (HLS) and integrated with DistilBERT for Q, K, V projections, our accelerator achieves significant speedup and energy efficiency gains over CPU baselines. Standalone GEMM benchmarks show up to a 7x speedup over an ARM CPU (PyTorch) and ~200x over naive numpy, with a throughput of up to 3.1 GFLOPs on 768x3072 matrices. Although the overall end-to-end DistilBERT acceleration is more modest, our results validate the potential of FPGA-based acceleration for critical components of Transformer models.

We present 3D Spatial MultiModal Memory (M3), a multimodal memory system designed to retain information about medium-sized static scenes through video sources for visual perception. By integrating 3D Gaussian Splatting techniques with foundation models, M3 builds a multimodal memory capable of rendering feature representations across granularities, encompassing a wide range of knowledge. In our exploration, we identify two key challenges in previous works on feature splatting: (1) computational constraints in storing high-dimensional features for each Gaussian primitive, and (2) misalignment or information loss between distilled features and foundation model features. To address these challenges, we propose M3 with key components of principal scene components and Gaussian memory attention, enabling efficient training and inference. To validate M3, we conduct comprehensive quantitative evaluations of feature similarity and downstream tasks, as well as qualitative visualizations to highlight the pixel trace of Gaussian memory attention. Our approach encompasses a diverse range of foundation models, including vision-language models (VLMs), perception models, and large multimodal and language models (LMMs/LLMs). Furthermore, to demonstrate real-world applicability, we deploy M3's feature field in indoor scenes on a quadruped robot. Notably, we claim that M3 is the first work to address the core compression challenges in 3D feature distillation.

In zero-shot image recognition tasks, humans demonstrate remarkable flexibility in classifying unseen categories by composing known simpler concepts. However, existing vision-language models (VLMs), despite achieving significant progress through large-scale natural language supervision, often underperform in real-world applications because of sub-optimal prompt engineering and the inability to adapt effectively to target classes. To address these issues, we propose a Concept-guided Human-like Bayesian Reasoning (CHBR) framework. Grounded in Bayes' theorem, CHBR models the concept used in human image recognition as latent variables and formulates this task by summing across potential concepts, weighted by a prior distribution and a likelihood function. To tackle the intractable computation over an infinite concept space, we introduce an importance sampling algorithm that iteratively prompts large language models (LLMs) to generate discriminative concepts, emphasizing inter-class differences. We further propose three heuristic approaches involving Average Likelihood, Confidence Likelihood, and Test Time Augmentation (TTA) Likelihood, which dynamically refine the combination of concepts based on the test image. Extensive evaluations across fifteen datasets demonstrate that CHBR consistently outperforms existing state-of-the-art zero-shot generalization methods.

Foundation models have emerged as a powerful paradigm in computational pathology (CPath), enabling scalable and generalizable analysis of histopathological images. While early developments centered on uni-modal models trained solely on visual data, recent advances have highlighted the promise of multi-modal foundation models that integrate heterogeneous data sources such as textual reports, structured domain knowledge, and molecular profiles. In this survey, we provide a comprehensive and up-to-date review of multi-modal foundation models in CPath, with a particular focus on models built upon hematoxylin and eosin (H&E) stained whole slide images (WSIs) and tile-level representations. We categorize 32 state-of-the-art multi-modal foundation models into three major paradigms: vision-language, vision-knowledge graph, and vision-gene expression. We further divide vision-language models into non-LLM-based and LLM-based approaches. Additionally, we analyze 28 available multi-modal datasets tailored for pathology, grouped into image-text pairs, instruction datasets, and image-other modality pairs. Our survey also presents a taxonomy of downstream tasks, highlights training and evaluation strategies, and identifies key challenges and future directions. We aim for this survey to serve as a valuable resource for researchers and practitioners working at the intersection of pathology and AI.

Large Language Models $($LLMs$)$ solve complex problems using training-free methods like prompt engineering and in-context learning, yet ensuring reasoning correctness remains challenging. While self-correction methods such as self-consistency and self-refinement aim to improve reliability, they often reinforce biases due to the lack of effective feedback mechanisms. Multi-Agent Debate $($MAD$)$ has emerged as an alternative, but we identify two key limitations: bias reinforcement, where debate amplifies model biases instead of correcting them, and lack of perspective diversity, as all agents share the same model and reasoning patterns, limiting true debate effectiveness. To systematically evaluate these issues, we introduce $\textit{MetaNIM Arena}$, a benchmark designed to assess LLMs in adversarial strategic decision-making, where dynamic interactions influence optimal decisions. To overcome MAD's limitations, we propose $\textbf{DReaMAD}$ $($$\textbf{D}$iverse $\textbf{Rea}$soning via $\textbf{M}$ulti-$\textbf{A}$gent $\textbf{D}$ebate with Refined Prompt$)$, a novel framework that $(1)$ refines LLM's strategic prior knowledge to improve reasoning quality and $(2)$ promotes diverse viewpoints within a single model by systematically modifying prompts, reducing bias. Empirical results show that $\textbf{DReaMAD}$ significantly improves decision accuracy, reasoning diversity, and bias mitigation across multiple strategic tasks, establishing it as a more effective approach for LLM-based decision-making.

Quantifying the realism of images remains a challenging problem in the field of artificial intelligence. For example, an image of Albert Einstein holding a smartphone violates common-sense because modern smartphone were invented after Einstein's death. We introduce a novel method for assessing image realism using Large Vision-Language Models (LVLMs) and Natural Language Inference (NLI). Our approach is based on the premise that LVLMs may generate hallucinations when confronted with images that defy common sense. Using LVLM to extract atomic facts from these images, we obtain a mix of accurate facts and erroneous hallucinations. We proceed by calculating pairwise entailment scores among these facts, subsequently aggregating these values to yield a singular reality score. This process serves to identify contradictions between genuine facts and hallucinatory elements, signaling the presence of images that violate common sense. Our approach has achieved a new state-of-the-art performance in zero-shot mode on the WHOOPS!

Time complexity is a theoretic measure to determine the amount of time the algorithm needs for its execution. In reality, developers write algorithms into code snippets within limited resources, making the calculation of a code's time complexity a fundamental task. However, determining the precise time complexity of a code is theoretically undecidable. In response, recent advancements have leaned toward deploying datasets for code time complexity prediction and initiating preliminary experiments for this challenge. We investigate the challenge in low-resource scenarios where only a few labeled instances are given for training. Remarkably, we are the first to introduce TCProF: a Time-Complexity Prediction SSL Framework as an effective solution for code time complexity prediction in low-resource settings. TCProF significantly boosts performance by integrating our augmentation, symbolic modules, and a co-training mechanism, achieving a more than 60% improvement over self-training approaches. We further provide an extensive comparative analysis between TCProF, ChatGPT, and Gemini-Pro, offering a detailed evaluation of our approach. Our code is at https://github.com/peer0/few-shot-tc.

Recently, Test-Time Scaling Large Language Models (LLMs), such as DeepSeek-R1 and OpenAI o1, have demonstrated exceptional capabilities across various domains and tasks, particularly in reasoning. While these models have shown impressive performance on general language tasks, their effectiveness in specialized fields like legal remains unclear. To address this, we present a preliminary evaluation of LLMs in various legal scenarios, covering both Chinese and English legal tasks. Our analysis includes 9 LLMs and 17 legal tasks, with a focus on newly published and more complex challenges such as multi-defendant legal judgments and legal argument reasoning. Our findings indicate that, despite DeepSeek-R1 and OpenAI o1 being among the most powerful models, their legal reasoning capabilities are still lacking. Specifically, these models score below 80\% on seven Chinese legal reasoning tasks and below 80\% on two English legal reasoning tasks. This suggests that, even among the most advanced reasoning models, legal reasoning abilities remain underdeveloped.

Scaling architectures have been proven effective for improving Scene Text Recognition (STR), but the individual contribution of vision encoder and text decoder scaling remain under-explored. In this work, we present an in-depth empirical analysis and demonstrate that, contrary to previous observations, scaling the decoder yields significant performance gains, always exceeding those achieved by encoder scaling alone. We also identify label noise as a key challenge in STR, particularly in real-world data, which can limit the effectiveness of STR models. To address this, we propose Cloze Self-Distillation (CSD), a method that mitigates label noise by distilling a student model from context-aware soft predictions and pseudolabels generated by a teacher model. Additionally, we enhance the decoder architecture by introducing differential cross-attention for STR. Our methodology achieves state-of-the-art performance on 10 out of 11 benchmarks using only real data, while significantly reducing the parameter size and computational costs.