PyTorchKR Papers

최신 논문

총 6,086편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2312.01823공식 코드 · Papers with Code

Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication

Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique. Despite this progress, their reasoning is often constrained by their intrinsic understanding, lacking external insights. To address this, we propose Exchange-of-Thought (EoT), a novel framework that enables cross-model communication during problem-solving. Drawing inspiration from network topology, EoT integrates four unique communication paradigms: Memory, Report, Relay, and Debate. This paper delves into the communication dynamics and volume associated with each paradigm. To counterbalance the risks of incorrect reasoning chains, we implement a robust confidence evaluation mechanism within these communications. Our experiments across diverse complex reasoning tasks demonstrate that EoT significantly surpasses established baselines, underscoring the value of external insights in enhancing LLM performance. Furthermore, we show that EoT achieves these superior results in a cost-effective manner, marking a promising advancement for efficient and collaborative AI problem-solving.

arXiv:2312.00842공식 코드 · Papers with Code

ESM-NBR: fast and accurate nucleic acid-binding residue prediction via protein language model feature representation and multi-task learning

Protein-nucleic acid interactions play a very important role in a variety of biological activities. Accurate identification of nucleic acid-binding residues is a critical step in understanding the interaction mechanisms. Although many computationally based methods have been developed to predict nucleic acid-binding residues, challenges remain. In this study, a fast and accurate sequence-based method, called ESM-NBR, is proposed. In ESM-NBR, we first use the large protein language model ESM2 to extract discriminative biological properties feature representation from protein primary sequences; then, a multi-task deep learning model composed of stacked bidirectional long short-term memory (BiLSTM) and multi-layer perceptron (MLP) networks is employed to explore common and private information of DNA- and RNA-binding residues with ESM2 feature as input. Experimental results on benchmark data sets demonstrate that the prediction performance of ESM2 feature representation comprehensively outperforms evolutionary information-based hidden Markov model (HMM) features. Meanwhile, the ESM-NBR obtains the MCC values for DNA-binding residues prediction of 0.427 and 0.391 on two independent test sets, which are 18.61 and 10.45% higher than those of the second-best methods, respectively. Moreover, by completely discarding the time-cost multiple sequence alignment process, the prediction speed of ESM-NBR far exceeds that of existing methods (5.52s for a protein sequence of length 500, which is about 16 times faster than the second-fastest method). A user-friendly standalone package and the data of ESM-NBR are freely available for academic use at: https://github.com/wwzll123/ESM-NBR.

arXiv:2312.01435공식 코드 · Papers with Code

Automatic Report Generation for Histopathology images using pre-trained Vision Transformers and BERT

Deep learning for histopathology has been successfully used for disease classification, image segmentation and more. However, combining image and text modalities using current state-of-the-art (SOTA) methods has been a challenge due to the high resolution of histopathology images. Automatic report generation for histopathology images is one such challenge. In this work, we show that using an existing pre-trained Vision Transformer (ViT) to encode 4096x4096 sized patches of the Whole Slide Image (WSI) and a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model for language modeling-based decoder for report generation, we can build a performant and portable report generation mechanism that takes into account the whole high resolution image. Our method allows us to not only generate and evaluate captions that describe the image, but also helps us classify the image into tissue types and the gender of the patient as well. Our best performing model achieves a 89.52% accuracy in Tissue Type classification with a BLEU-4 score of 0.12 in our caption generation task.

arXiv:2312.02142공식 코드 · Papers with Code

Object Recognition as Next Token Prediction

We present an approach to pose object recognition as next token prediction. The idea is to apply a language decoder that auto-regressively predicts the text tokens from image embeddings to form labels. To ground this prediction process in auto-regression, we customize a non-causal attention mask for the decoder, incorporating two key features: modeling tokens from different labels to be independent, and treating image tokens as a prefix. This masking mechanism inspires an efficient method - one-shot sampling - to simultaneously sample tokens of multiple labels in parallel and rank generated labels by their probabilities during inference. To further enhance the efficiency, we propose a simple strategy to construct a compact decoder by simply discarding the intermediate blocks of a pretrained language model. This approach yields a decoder that matches the full model's performance while being notably more efficient. The code is available at https://github.com/kaiyuyue/nxtp

arXiv:2312.01886공식 코드 · Papers with Code

InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Large vision-language models (LVLMs) have demonstrated their incredible capability in image understanding and response generation. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we formulate a novel and practical targeted attack scenario that the adversary can only know the vision encoder of the victim LVLM, without the knowledge of its prompts (which are often proprietary for service providers and not publicly available) and its underlying large language model (LLM). This practical setting poses challenges to the cross-prompt and cross-model transferability of targeted adversarial attack, which aims to confuse the LVLM to output a response that is semantically similar to the attacker's chosen target text. To this end, we propose an instruction-tuned targeted attack (dubbed \textsc{InstructTA}) to deliver the targeted adversarial attack on LVLMs with high transferability. Initially, we utilize a public text-to-image generative model to "reverse" the target response into a target image, and employ GPT-4 to infer a reasonable instruction $\boldsymbol{p}^\prime$ from the target response. We then form a local surrogate model (sharing the same vision encoder with the victim LVLM) to extract instruction-aware features of an adversarial image example and the target image, and minimize the distance between these two features to optimize the adversarial example. To further improve the transferability with instruction tuning, we augment the instruction $\boldsymbol{p}^\prime$ with instructions paraphrased from GPT-4. Extensive experiments demonstrate the superiority of our proposed method in targeted attack performance and transferability. The code is available at https://github.com/xunguangwang/InstructTA.

arXiv:2312.02051공식 코드 · Papers with Code

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding

This work proposes TimeChat, a time-sensitive multimodal large language model specifically designed for long video understanding. Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds visual content with the timestamp of each frame, and (2) a sliding video Q-Former that produces a video token sequence of varying lengths to accommodate videos of various durations. Additionally, we construct an instruction-tuning dataset, encompassing 6 tasks and a total of 125K instances, to further enhance TimeChat's instruction-following performance. Experiment results across various video understanding tasks, such as dense captioning, temporal grounding, and highlight detection, demonstrate TimeChat's strong zero-shot temporal localization and reasoning capabilities. For example, it achieves +9.2 F1 score and +2.8 CIDEr on YouCook2, +5.8 HIT@1 on QVHighlights, and +27.5 R@1 (IoU=0.5) on Charades-STA, compared to state-of-the-art video large language models, holding the potential to serve as a versatile video assistant for long-form video comprehension tasks and satisfy realistic user requirements.

arXiv:2312.01648공식 코드 · Papers with Code

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation

Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In particular, we develop in closed form $(i)$ the intrinsic dimension in which the Multi-Head Attention embeddings are constrained to exist and $(ii)$ the partition and per-region affine mappings of the feedforward (MLP) network of LLMs' layers. Our theoretical findings further enable the design of novel principled solutions applicable to state-of-the-art LLMs. First, we show that, through our geometric understanding, we can bypass LLMs' RLHF protection by controlling the embedding's intrinsic dimension through informed prompt manipulation. Second, we derive interpretable geometrical features that can be extracted from any (pre-trained) LLM, providing a rich abstract representation of their inputs. We observe that these features are sufficient to help solve toxicity detection, and even allow the identification of various types of toxicity. Our results demonstrate how, even in large-scale regimes, exact theoretical results can answer practical questions in LLMs. Code: https://github.com/RandallBalestriero/SplineLLM

arXiv:2305.09656공식 코드 · Papers with Code

SatLM: Satisfiability-Aided Language Models Using Declarative Prompting

Prior work has combined chain-of-thought prompting in large language models (LLMs) with programmatic representations to perform effective and transparent reasoning. While such an approach works well for tasks that only require forward reasoning (e.g., straightforward arithmetic), it is less effective for constraint solving problems that require more sophisticated planning and search. In this paper, we propose a new satisfiability-aided language modeling (SatLM) approach for improving the reasoning capabilities of LLMs. We use an LLM to generate a declarative task specification rather than an imperative program and leverage an off-the-shelf automated theorem prover to derive the final answer. This approach has two key advantages. The declarative specification is closer to the problem description than the reasoning steps are, so the LLM can parse it out of the description more accurately. Furthermore, by offloading the actual reasoning task to an automated theorem prover, our approach can guarantee the correctness of the answer with respect to the parsed specification and avoid planning errors in the solving process. We evaluate SATLM on 8 different datasets and show that it consistently outperforms program-aided LMs in the imperative paradigm. In particular, SATLM outperforms program-aided LMs by 23% on a challenging subset of the GSM arithmetic reasoning dataset; SATLM also achieves a new SoTA on LSAT and BoardgameQA, surpassing previous models that are trained on the respective training sets.

arXiv:2305.03047공식 코드 · Papers with Code

Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of large language models (LLMs) with human intentions, ensuring they are helpful, ethical, and reliable. However, this dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision and the related issues on quality, reliability, diversity, self-consistency, and undesirable biases. To address these challenges, we propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision. Our approach encompasses four stages: first, we use an LLM to generate synthetic prompts, and a topic-guided method to augment the prompt diversity; second, we use a small set of human-written principles for AI models to follow, and guide the LLM through in-context learning from demonstrations (of principles application) to produce helpful, ethical, and reliable responses to user's queries; third, we fine-tune the original LLM with the high-quality self-aligned responses so that the resulting model can generate desirable responses for each query directly without the principle set and the demonstrations anymore; and finally, we offer a refinement step to address the issues of overly-brief or indirect responses. Applying SELF-ALIGN to the LLaMA-65b base language model, we develop an AI assistant named Dromedary. With fewer than 300 lines of human annotations (including < 200 seed prompts, 16 generic principles, and 5 exemplars for in-context learning). Dromedary significantly surpasses the performance of several state-of-the-art AI systems, including Text-Davinci-003 and Alpaca, on benchmark datasets with various settings.

arXiv:2312.01191공식 코드 · Papers with Code

Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning

Recently, remote sensing image captioning has gained significant attention in the remote sensing community. Due to the significant differences in spatial resolution of remote sensing images, existing methods in this field have predominantly concentrated on the fine-grained extraction of remote sensing image features, but they cannot effectively handle the semantic consistency between visual features and textual features. To efficiently align the image-text, we propose a novel two-stage vision-language pre-training-based approach to bootstrap interactive image-text alignment for remote sensing image captioning, called BITA, which relies on the design of a lightweight interactive Fourier Transformer to better align remote sensing image-text features. The Fourier layer in the interactive Fourier Transformer is capable of extracting multi-scale features of remote sensing images in the frequency domain, thereby reducing the redundancy of remote sensing visual features. Specifically, the first stage involves preliminary alignment through image-text contrastive learning, which aligns the learned multi-scale remote sensing features from the interactive Fourier Transformer with textual features. In the second stage, the interactive Fourier Transformer connects the frozen image encoder with a large language model. Then, prefix causal language modeling is utilized to guide the text generation process using visual features. Ultimately, across the UCM-caption, RSICD, and NWPU-caption datasets, the experimental results clearly demonstrate that BITA outperforms other advanced comparative approaches. The code is available at https://github.com/yangcong356/BITA.

arXiv:2306.11197공식 코드 · Papers with Code

Sparse Modular Activation for Efficient Sequence Modeling

Recent hybrid models combining Linear State Space Models (SSMs) with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. However, current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. To address this limitation, we introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely and dynamically activate sub-modules for sequence elements in a differentiable manner. Through allowing each element to skip non-activated sub-modules, SMA reduces computation and memory consumption of neural networks at both training and inference stages. To validate the effectiveness of SMA on sequence modeling, we design a novel neural architecture, SeqBoat, which employs SMA to sparsely activate a Gated Attention Unit (GAU) based on the state representations learned from an SSM. By constraining the GAU to only conduct local attention on the activated inputs, SeqBoat can achieve linear inference complexity with theoretically infinite attention span, and provide substantially better quality-efficiency trade-off than the chunking-based models. With experiments on a wide range of tasks, including long sequence modeling, speech classification and language modeling, SeqBoat brings new state-of-the-art results among hybrid models with linear complexity, and reveals the amount of attention needed for each task through the learned sparse activation patterns. Our code is publicly available at https://github.com/renll/SeqBoat.

arXiv:2305.16646공식 코드 · Papers with Code

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

Large language models have shown astonishing performance on a wide range of reasoning tasks. In this paper, we investigate whether they could reason about real-world events and help improve the prediction performance of event sequence models. We design LAMP, a framework that integrates a large language model in event prediction. Particularly, the language model performs abductive reasoning to assist an event sequence model: the event model proposes predictions on future events given the past; instructed by a few expert-annotated demonstrations, the language model learns to suggest possible causes for each proposal; a search module finds out the previous events that match the causes; a scoring function learns to examine whether the retrieved events could actually cause the proposal. Through extensive experiments on several challenging real-world datasets, we demonstrate that our framework -- thanks to the reasoning capabilities of large language models -- could significantly outperform the state-of-the-art event sequence models.

arXiv:2312.00249공식 코드 · Papers with Code

Acoustic Prompt Tuning: Empowering Large Language Models with Audition Capabilities

The auditory system plays a substantial role in shaping the overall human perceptual experience. While prevailing large language models (LLMs) and visual language models (VLMs) have shown their promise in solving a wide variety of language and vision understanding tasks, only a few of them can be generalised to the audio domain without compromising their domain-specific capability. In this work, we introduce Acoustic Prompt Tuning (APT), a new adapter extending LLMs and VLMs to the audio domain by injecting audio embeddings to the input of LLMs, namely soft prompting. Specifically, APT applies an instruction-aware audio aligner to generate soft prompts, conditioned on both input text and sounds, as the inputs to the language model. To mitigate data scarcity in the audio domain, a curriculum learning strategy is proposed by formulating diverse audio tasks in a sequential manner. Moreover, we improve the audio language model by using interleaved audio-text embeddings as the input sequence. In this improved model, zero constraints are imposed on the input format, thus it is capable of tackling diverse modelling tasks, such as few-shot audio classification and audio comparison. To further evaluate the advanced ability of the audio networks, we introduce natural language audio reasoning (NLAR), a new task that analyses two audio clips by comparison and summarisation. Experiments show that APT-enhanced LLMs (namely APT-LLMs) achieve competitive results compared to the expert models (i.e., the networks trained on the target datasets) across various tasks. We finally demonstrate APT's ability in extending frozen VLMs to the audio domain without fine-tuning, achieving promising results in audio-visual question and answering. Our code and model weights will be released at https://github.com/JinhuaLiang/APT

arXiv:2312.00096공식 코드 · Papers with Code

OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition

Due to the resource-intensive nature of training vision-language models on expansive video data, a majority of studies have centered on adapting pre-trained image-language models to the video domain. Dominant pipelines propose to tackle the visual discrepancies with additional temporal learners while overlooking the substantial discrepancy for web-scaled descriptive narratives and concise action category names, leading to less distinct semantic space and potential performance limitations. In this work, we prioritize the refinement of text knowledge to facilitate generalizable video recognition. To address the limitations of the less distinct semantic space of category names, we prompt a large language model (LLM) to augment action class names into Spatio-Temporal Descriptors thus bridging the textual discrepancy and serving as a knowledge base for general recognition. Moreover, to assign the best descriptors with different video instances, we propose Optimal Descriptor Solver, forming the video recognition problem as solving the optimal matching flow across frame-level representations and descriptors. Comprehensive evaluations in zero-shot, few-shot, and fully supervised video recognition highlight the effectiveness of our approach. Our best model achieves a state-of-the-art zero-shot accuracy of 75.1% on Kinetics-600.

arXiv:2312.00663공식 코드 · Papers with Code

Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignment

Deep neural network models have achieved remarkable progress in 3D scene understanding while trained in the closed-set setting and with full labels. However, the major bottleneck is that these models do not have the capacity to recognize any unseen novel classes beyond the training categories in diverse real-world applications. Therefore, we are in urgent need of a framework that can simultaneously be applicable to both 3D point cloud segmentation and detection, particularly in the circumstances where the labels are rather scarce. This work presents a generalized and straightforward framework for dealing with 3D scene understanding when the labeled scenes are quite limited. To extract knowledge for novel categories from the pre-trained vision-language models, we propose a hierarchical feature-aligned pre-training and knowledge distillation strategy to extract and distill meaningful information from large-scale vision-language models, which helps benefit the open-vocabulary scene understanding tasks. To encourage latent instance discrimination and to guarantee efficiency, we propose the unsupervised region-level semantic contrastive learning scheme for point clouds, using confident predictions of the neural network to discriminate the intermediate feature embeddings at multiple stages. In the limited reconstruction case, our proposed approach, termed WS3D++, ranks 1st on the large-scale ScanNet benchmark on both the task of semantic segmentation and instance segmentation. Extensive experiments with both indoor and outdoor scenes demonstrated the effectiveness of our approach in both data-efficient learning and open-world few-shot learning. The code is made publicly available at: https://drive.google.com/drive/folders/1M58V-PtR8DBEwD296zJkNg_m2qq-MTAP?usp=sharing.

arXiv:2312.00774공식 코드 · Papers with Code

Context Retrieval via Normalized Contextual Latent Interaction for Conversational Agent

Conversational agents leveraging AI, particularly deep learning, are emerging in both academic research and real-world applications. However, these applications still face challenges, including disrespecting knowledge and facts, not personalizing to user preferences, and enormous demand for computational resources during training and inference. Recent research efforts have been focused on addressing these challenges from various aspects, including supplementing various types of auxiliary information to the conversational agents. However, existing methods are still not able to effectively and efficiently exploit relevant information from these auxiliary supplements to further unleash the power of the conversational agents and the language models they use. In this paper, we present a novel method, PK-NCLI, that is able to accurately and efficiently identify relevant auxiliary information to improve the quality of conversational responses by learning the relevance among persona, chat history, and knowledge background through low-level normalized contextual latent interaction. Our experimental results indicate that PK-NCLI outperforms the state-of-the-art method, PK-FoCus, by 47.80%/30.61%/24.14% in terms of perplexity, knowledge grounding, and training efficiency, respectively, and maintained the same level of persona grounding performance. We also provide a detailed analysis of how different factors, including language model choices and trade-offs on training weights, would affect the performance of PK-NCLI.

arXiv:2312.00752공식 코드 · Papers with Code

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention, gated convolution and recurrent models, and structured state space models (SSMs) have been developed to address Transformers' computational inefficiency on long sequences, but they have not performed as well as attention on important modalities such as language. We identify that a key weakness of such models is their inability to perform content-based reasoning, and make several improvements. First, simply letting the SSM parameters be functions of the input addresses their weakness with discrete modalities, allowing the model to selectively propagate or forget information along the sequence length dimension depending on the current token. Second, even though this change prevents the use of efficient convolutions, we design a hardware-aware parallel algorithm in recurrent mode. We integrate these selective SSMs into a simplified end-to-end neural network architecture without attention or even MLP blocks (Mamba). Mamba enjoys fast inference (5$\times$ higher throughput than Transformers) and linear scaling in sequence length, and its performance improves on real data up to million-length sequences. As a general sequence model backbone, Mamba achieves state-of-the-art performance across several modalities such as language, audio, and genomics. On language modeling, our Mamba-3B model outperforms Transformers of the same size and matches Transformers twice its size, both in pretraining and downstream evaluation.

arXiv:2312.00273공식 코드 · Papers with Code

Mark My Words: Analyzing and Evaluating Language Model Watermarks

The capabilities of large language models have grown significantly in recent years and so too have concerns about their misuse. It is important to be able to distinguish machine-generated text from human-authored content. Prior works have proposed numerous schemes to watermark text, which would benefit from a systematic evaluation framework. This work focuses on LLM output watermarking techniques - as opposed to image or model watermarks - and proposes Mark My Words, a comprehensive benchmark for them under different natural language tasks. We focus on three main metrics: quality, size (i.e., the number of tokens needed to detect a watermark), and tamper resistance (i.e., the ability to detect a watermark after perturbing marked text). Current watermarking techniques are nearly practical enough for real-world use: Kirchenbauer et al. [33]'s scheme can watermark models like Llama 2 7B-chat or Mistral-7B-Instruct with no perceivable loss in quality on natural language tasks, the watermark can be detected with fewer than 100 tokens, and their scheme offers good tamper resistance to simple perturbations. However, they struggle to efficiently watermark code generations. We publicly release our benchmark (https://github.com/wagner-group/MarkMyWords).

arXiv:2311.17963공식 코드 · Papers with Code

M$^{2}$Chat: Empowering VLM for Multimodal LLM Interleaved Text-Image Generation

While current LLM chatbots like GPT-4V bridge the gap between human instructions and visual representations to enable text-image generations, they still lack efficient alignment methods for high-fidelity performance on multiple downstream tasks. In this paper, we propose \textbf{$M^{2}Chat$}, a novel unified multimodal LLM framework for generating interleaved text-image conversation across various scenarios. Specifically, we propose an $M^{3}Adapter$ that efficiently integrates granular low-level visual information and high-level semantic features from multi-modality prompts. Upon the well-aligned fused feature, $M^{3}Adapter$ tailors a learnable gating strategy to balance the model creativity and consistency across various tasks adaptively. Moreover, to further enhance the effectiveness of $M^{3}Adapter$ while preserving the coherence of semantic context comprehension, we introduce a two-stage $M^{3}FT$ fine-tuning strategy. This strategy optimizes disjoint groups of parameters for image-text alignment and visual-instruction respectively. Extensive experiments demonstrate our $M^{2}Chat$ surpasses state-of-the-art counterparts across diverse benchmarks, showcasing its prowess in interleaving generation, storytelling, and multimodal dialogue systems. The demo and code are available at \red{https://mattie-e.github.io/M2Chat.github.io}.

arXiv:2311.17945공식 코드 · Papers with Code

Contrastive Vision-Language Alignment Makes Efficient Instruction Learner

We study the task of extending the large language model (LLM) into a vision-language instruction-following model. This task is crucial but challenging since the LLM is trained on text modality only, making it hard to effectively digest the visual modality. To address this, existing methods typically train a visual adapter to align the representation between a pre-trained vision transformer (ViT) and the LLM by a generative image captioning loss. However, we find that the generative objective can only produce weak alignment for vision and language, making the aligned vision-language model very hungry for the instruction fine-tuning data. In this paper, we propose CG-VLM that applies both Contrastive and Generative alignment objectives to effectively align the representation of ViT and LLM. Different from image level and sentence level alignment in common contrastive learning settings, CG-VLM aligns the image-patch level features and text-token level embeddings, which, however, is very hard to achieve as no explicit grounding patch-token relation provided in standard image captioning datasets. To address this issue, we propose to maximize the averaged similarity between pooled image-patch features and text-token embeddings. Extensive experiments demonstrate that the proposed CG-VLM produces strong vision-language alignment and is an efficient instruction learner. For example, using only 10% instruction tuning data, we reach 95% performance of state-of-the-art method LLaVA [29] on the zero-shot ScienceQA-Image benchmark.