Recent advances in Reasoning LLMs (e.g., DeepSeek-R1 and OpenAI-o1) have showcased impressive reasoning capabilities via reinforcement learning. However, extending these capabilities to Multimodal LLMs (MLLMs) is hampered by the prohibitive costs of retraining and the scarcity of high-quality, verifiable multimodal reasoning datasets. This paper introduces FRANK Model, a training-FRee ANd r1-liKe MLLM that imbues off-the-shelf MLLMs with reasoning and reflection abilities, without any gradient updates or extra supervision. Our key insight is to decouple perception and reasoning across MLLM decoder layers. Specifically, we observe that compared to the deeper decoder layers, the shallow decoder layers allocate more attention to visual tokens, while the deeper decoder layers concentrate on textual semantics. This observation motivates a hierarchical weight merging approach that combines a visual-pretrained MLLM with a reasoning-specialized LLM. To this end, we propose a layer-wise, Taylor-derived closed-form fusion mechanism that integrates reasoning capacity into deep decoder layers while preserving visual grounding in shallow decoder layers. Extensive experiments on challenging multimodal reasoning benchmarks demonstrate the effectiveness of our approach. On the MMMU benchmark, our model FRANK-38B achieves an accuracy of 69.2, outperforming the strongest baseline InternVL2.5-38B by +5.3, and even surpasses the proprietary GPT-4o model. Our project homepage is at: http://iip.whu.edu.cn/frank/index.html
We present the new bidirectional variational autoencoder (BVAE) network architecture. The BVAE uses a single neural network both to encode and decode instead of an encoder-decoder network pair. The network encodes in the forward direction and decodes in the backward direction through the same synaptic web. Simulations compared BVAEs and ordinary VAEs on the four image tasks of image reconstruction, classification, interpolation, and generation. The image datasets included MNIST handwritten digits, Fashion-MNIST, CIFAR-10, and CelebA-64 face images. The bidirectional structure of BVAEs cut the parameter count by almost 50% and still slightly outperformed the unidirectional VAEs.
To encode point clouds containing both geometry and attributes, most learning-based compression schemes treat geometry and attribute coding separately, employing distinct encoders and decoders. This not only increases computational complexity but also fails to fully exploit shared features between geometry and attributes. To address this limitation, we propose SEDD-PCC, an end-to-end learning-based framework for lossy point cloud compression that jointly compresses geometry and attributes. SEDD-PCC employs a single encoder to extract shared geometric and attribute features into a unified latent space, followed by dual specialized decoders that sequentially reconstruct geometry and attributes. Additionally, we incorporate knowledge distillation to enhance feature representation learning from a teacher model, further improving coding efficiency. With its simple yet effective design, SEDD-PCC provides an efficient and practical solution for point cloud compression. Comparative evaluations against both rule-based and learning-based methods demonstrate its competitive performance, highlighting SEDD-PCC as a promising AI-driven compression approach.
Automatic detection of speech dysfluency aids speech-language pathologists in efficient transcription of disordered speech, enhancing diagnostics and treatment planning. Traditional methods, often limited to classification, provide insufficient clinical insight, and text-independent models misclassify dysfluency, especially in context-dependent cases. This work introduces Dysfluent-WFST, a zero-shot decoder that simultaneously transcribes phonemes and detects dysfluency. Unlike previous models, Dysfluent-WFST operates with upstream encoders like WavLM and requires no additional training. It achieves state-of-the-art performance in both phonetic error rate and dysfluency detection on simulated and real speech data. Our approach is lightweight, interpretable, and effective, demonstrating that explicit modeling of pronunciation behavior in decoding, rather than complex architectures, is key to improving dysfluency processing systems.
In this paper, we propose to compress human body video with interactive semantics, which can facilitate video coding to be interactive and controllable by manipulating semantic-level representations embedded in the coded bitstream. In particular, the proposed encoder employs a 3D human model to disentangle nonlinear dynamics and complex motion of human body signal into a series of configurable embeddings, which are controllably edited, compactly compressed, and efficiently transmitted. Moreover, the proposed decoder can evolve the mesh-based motion fields from these decoded semantics to realize the high-quality human body video reconstruction. Experimental results illustrate that the proposed framework can achieve promising compression performance for human body videos at ultra-low bitrate ranges compared with the state-of-the-art video coding standard Versatile Video Coding (VVC) and the latest generative compression schemes. Furthermore, the proposed framework enables interactive human body video coding without any additional pre-/post-manipulation processes, which is expected to shed light on metaverse-related digital human communication in the future.
Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual settings. They are also often unable to generalize for speakers of unseen languages and accents. In this paper, we adopt a simple yet effective approach that combines discrete speech representations from self-supervised models with a non-autoregressive Diffusion-Transformer based conditional flow matching speech decoder. We show that this architecture allows us to train a voice-conversion model in a purely textless, self-supervised fashion. Our technique works without requiring multiple encoders to disentangle speech features. Our model also manages to excel in zero-shot cross-lingual settings even for unseen languages. For Demo: https://ez-vc.github.io/EZ-VC-Demo/
Wireless Fidelity (WiFi) based indoor positioning is a widely researched area for determining the position of devices within a wireless network. Accurate indoor location has numerous applications, such as asset tracking and indoor navigation. Despite advances in WiFi localization techniques -- in particular approaches that leverage WiFi telemetry -- their adoption in practice remains limited due to several factors including environmental changes that cause signal fading, multipath effects, interference, which, in turn, impact positioning accuracy. In addition, telemetry data differs depending on the WiFi device vendor, offering distinct features and formats; use case requirements can also vary widely. Currently, there is no unified model to handle all these variations effectively. In this paper, we present WiFiGPT, a Generative Pretrained Transformer (GPT) based system that is able to handle these variations while achieving high localization accuracy. Our experiments with WiFiGPT demonstrate that GPTs, in particular Large Language Models (LLMs), can effectively capture subtle spatial patterns in noisy wireless telemetry, making them reliable regressors. Compared to existing state-of-the-art methods, our method matches and often surpasses conventional approaches for multiple types of telemetry. Achieving sub-meter accuracy for RSSI and FTM and centimeter-level precision for CSI demonstrates the potential of LLM-based localisation to outperform specialized techniques, all without handcrafted signal processing or calibration.
Knowledge understanding is a foundational part of envisioned 6G networks to advance network intelligence and AI-native network architectures. In this paradigm, information extraction plays a pivotal role in transforming fragmented telecom knowledge into well-structured formats, empowering diverse AI models to better understand network terminologies. This work proposes a novel language model-based information extraction technique, aiming to extract structured entities from the telecom context. The proposed telecom structured entity extraction (TeleSEE) technique applies a token-efficient representation method to predict entity types and attribute keys, aiming to save the number of output tokens and improve prediction accuracy. Meanwhile, TeleSEE involves a hierarchical parallel decoding method, improving the standard encoder-decoder architecture by integrating additional prompting and decoding strategies into entity extraction tasks. In addition, to better evaluate the performance of the proposed technique in the telecom domain, we further designed a dataset named 6GTech, including 2390 sentences and 23747 words from more than 100 6G-related technical publications. Finally, the experiment shows that the proposed TeleSEE method achieves higher accuracy than other baseline techniques, and also presents 5 to 9 times higher sample processing speed.
Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods exhibit critical limitations: discrete search struggles with enormous combinatorial spaces, impeding practical use; and continuous search, being highly sensitive to initialization and step sizes, often becomes trapped in local optima, restricting global exploration. To overcome these limitations, DIFFT redefines FT as a reward-guided generative task. It first learns a compact and expressive latent space for feature sets using a Variational Auto-Encoder (VAE). A Latent Diffusion Model (LDM) then navigates this space to generate high-quality feature embeddings, its trajectory guided by a performance evaluator towards task-specific optima. This synthesis of global distribution learning (from LDM) and targeted optimization (reward guidance) produces potent embeddings, which a novel semi-autoregressive decoder efficiently converts into structured, discrete features, preserving intra-feature dependencies while allowing parallel inter-feature generation. Extensive experiments on 14 benchmark datasets show DIFFT consistently outperforms state-of-the-art baselines in predictive accuracy and robustness, with significantly lower training and inference times.
Large Language Models for code often entail significant computational complexity, which grows significantly with the length of the input code sequence. We propose LeanCode for code simplification to reduce training and prediction time, leveraging code contexts in utilizing attention scores to represent the tokens' importance. We advocate for the selective removal of tokens based on the average context-aware attention scores rather than average scores across all inputs. LeanCode uses the attention scores of `CLS' tokens within the encoder for classification tasks, such as code search. It also employs the encoder-decoder attention scores to determine token significance for sequence-to-sequence tasks like code summarization. Our evaluation shows LeanCode's superiority over the SOTAs DietCode and Slimcode, with improvements of 60% and 16% for code search, and 29% and 27% for code summarization, respectively.
Medical image captioning is a challenging task that requires generating clinically accurate and semantically meaningful descriptions of radiology images. While recent vision-language models (VLMs) such as BLIP, BLIP2, Gemini and ViT-GPT2 show strong performance on natural image datasets, they often produce generic or imprecise captions when applied to specialized medical domains. In this project, we explore the effectiveness of fine-tuning the BLIP model on the ROCO dataset for improved radiology captioning. We compare the fine-tuned BLIP against its zero-shot version, BLIP-2 base, BLIP-2 Instruct and a ViT-GPT2 transformer baseline. Our results demonstrate that domain-specific fine-tuning on BLIP significantly improves performance across both quantitative and qualitative evaluation metrics. We also visualize decoder cross-attention maps to assess interpretability and conduct an ablation study to evaluate the contributions of encoder-only and decoder-only fine-tuning. Our findings highlight the importance of targeted adaptation for medical applications and suggest that decoder-only fine-tuning (encoder-frozen) offers a strong performance baseline with 5% lower training time than full fine-tuning, while full model fine-tuning still yields the best results overall.
By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose perceptual organization? We finetune Stable Diffusion and MAE (encoder+decoder) for category-agnostic instance segmentation using our instance coloring loss exclusively on a narrow set of object types (indoor furnishings and cars). Surprisingly, our models exhibit strong zero-shot generalization, accurately segmenting objects of types and styles unseen in finetuning (and in many cases, MAE's ImageNet-1K pretraining too). Our best-performing models closely approach the heavily supervised SAM when evaluated on unseen object types and styles, and outperform it when segmenting fine structures and ambiguous boundaries. In contrast, existing promptable segmentation architectures or discriminatively pretrained models fail to generalize. This suggests that generative models learn an inherent grouping mechanism that transfers across categories and domains, even without internet-scale pretraining. Code, pretrained models, and demos are available on our website.
Large multimodal models excel in multimodal tasks but face significant computational challenges due to excessive computation on visual tokens. Unlike token reduction methods that focus on token-level redundancy, we identify and study the computation-level redundancy on vision tokens to ensure no information loss. Our key insight is that vision tokens from the pretrained vision encoder do not necessarily require all the heavy operations (e.g., self-attention, FFNs) in decoder-only LMMs and could be processed more lightly with proper designs. We designed a series of experiments to discover and progressively squeeze out the vision-related computation redundancy. Based on our findings, we propose ProxyV, a novel approach that utilizes proxy vision tokens to alleviate the computational burden on original vision tokens. ProxyV enhances efficiency without compromising performance and can even yield notable performance gains in scenarios with more moderate efficiency improvements. Furthermore, the flexibility of ProxyV is demonstrated through its combination with token reduction methods to boost efficiency further. The code will be made public at this https://github.com/penghao-wu/ProxyV URL.
We introduce Toto, a time series forecasting foundation model with 151 million parameters. Toto uses a modern decoder-only architecture coupled with architectural innovations designed to account for specific challenges found in multivariate observability time series data. Toto's pre-training corpus is a mixture of observability data, open datasets, and synthetic data, and is 4-10$\times$ larger than those of leading time series foundation models. Additionally, we introduce BOOM, a large-scale benchmark consisting of 350 million observations across 2,807 real-world time series. For both Toto and BOOM, we source observability data exclusively from Datadog's own telemetry and internal observability metrics. Extensive evaluations demonstrate that Toto achieves state-of-the-art performance on both BOOM and on established general purpose time series forecasting benchmarks. Toto's model weights, inference code, and evaluation scripts, as well as BOOM's data and evaluation code, are all available as open source under the Apache 2.0 License available at https://huggingface.co/Datadog/Toto-Open-Base-1.0 and https://github.com/DataDog/toto.
Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising improvements. However, these methods often lack a thorough analysis of their expressiveness and suffer from effective benchmarks for a fair evaluation. In this paper, we propose a unified framework to assess the expressiveness of existing methods, highlighting the impact of dual embeddings and decoder design on directed link prediction performance. To address limitations in current benchmark setups, we introduce DirLinkBench, a robust new benchmark with comprehensive coverage, standardized evaluation, and modular extensibility. The results on DirLinkBench show that current methods struggle to achieve strong performance, while DiGAE outperforms other baselines overall. We further revisit DiGAE theoretically, showing its graph convolution aligns with GCN on an undirected bipartite graph. Inspired by these insights, we propose a novel Spectral Directed Graph Auto-Encoder SDGAE that achieves state-of-the-art average performance on DirLinkBench. Finally, we analyze key factors influencing directed link prediction and highlight open challenges in this field.
Citation classification, which identifies the intention behind academic citations, is pivotal for scholarly analysis. Previous works suggest fine-tuning pretrained language models (PLMs) on citation classification datasets, reaping the reward of the linguistic knowledge they gained during pretraining. However, directly fine-tuning for citation classification is challenging due to labeled data scarcity, contextual noise, and spurious keyphrase correlations. In this paper, we present a novel framework, Citss, that adapts the PLMs to overcome these challenges. Citss introduces self-supervised contrastive learning to alleviate data scarcity, and is equipped with two specialized strategies to obtain the contrastive pairs: sentence-level cropping, which enhances focus on target citations within long contexts, and keyphrase perturbation, which mitigates reliance on specific keyphrases. Compared with previous works that are only designed for encoder-based PLMs, Citss is carefully developed to be compatible with both encoder-based PLMs and decoder-based LLMs, to embrace the benefits of enlarged pretraining. Experiments with three benchmark datasets with both encoder-based PLMs and decoder-based LLMs demonstrate our superiority compared to the previous state of the art. Our code is available at: github.com/LITONG99/Citss
With the rapid advancement of large language models like Gemini, GPT, and others, bridging the gap between the human brain and language processing has become an important area of focus. To address this challenge, researchers have developed various models to decode EEG signals into text. However, these models still face significant performance limitations. To overcome these shortcomings, we propose a new model, R1 Translator, which aims to improve the performance of EEG-to-text decoding. The R1 Translator model combines a bidirectional LSTM encoder with a pretrained transformer-based decoder, utilizing EEG features to produce high-quality text outputs. The model processes EEG embeddings through the LSTM to capture sequential dependencies, which are then fed into the transformer decoder for effective text generation. The R1 Translator excels in ROUGE metrics, outperforming both T5 (previous research) and Brain Translator. Specifically, R1 achieves a ROUGE-1 score of 38.00% (P), which is up to 9% higher than T5 (34.89%) and 3% better than Brain (35.69%). It also leads in ROUGE-L, with a F1 score of 32.51%, outperforming T5 by 3% (29.67%) and Brain by 2% (30.38%). In terms of CER, R1 achieves a CER of 0.5795, which is 2% lower than T5 (0.5917) and 4% lower than Brain (0.6001). Additionally, R1 performs better in WER with a score of 0.7280, outperforming T5 by 4.3% (0.7610) and Brain by 3.6% (0.7553). Code is available at https://github.com/Mmurrad/EEG-To-text.
Plane geometry problem solving (PGPS) has recently gained significant attention as a benchmark to assess the multi-modal reasoning capabilities of large vision-language models. Despite the growing interest in PGPS, the research community still lacks a comprehensive overview that systematically synthesizes recent work in PGPS. To fill this gap, we present a survey of existing PGPS studies. We first categorize PGPS methods into an encoder-decoder framework and summarize the corresponding output formats used by their encoders and decoders. Subsequently, we classify and analyze these encoders and decoders according to their architectural designs. Finally, we outline major challenges and promising directions for future research. In particular, we discuss the hallucination issues arising during the encoding phase within encoder-decoder architectures, as well as the problem of data leakage in current PGPS benchmarks.
Improving the skill of medium-range (1-8 day) severe weather prediction is crucial for mitigating societal impacts. This study introduces a novel approach leveraging decoder-only transformer networks to post-process AI-based weather forecasts, specifically from the Pangu-Weather model, for improved severe weather guidance. Unlike traditional post-processing methods that use a dense neural network to predict the probability of severe weather using discrete forecast samples, our method treats forecast lead times as sequential ``tokens'', enabling the transformer to learn complex temporal relationships within the evolving atmospheric state. We compare this approach against post-processing of the Global Forecast System (GFS) using both a traditional dense neural network and our transformer, as well as configurations that exclude convective parameters to fairly evaluate the impact of using the Pangu-Weather AI model. Results demonstrate that the transformer-based post-processing significantly enhances forecast skill compared to dense neural networks. Furthermore, AI-driven forecasts, particularly Pangu-Weather initialized from high resolution analysis, exhibit superior performance to GFS in the medium-range, even without explicit convective parameters. Our approach offers improved accuracy, and reliability, which also provides interpretability through feature attribution analysis, advancing medium-range severe weather prediction capabilities.
Given the audio-visual clip of the speaker, facial reaction generation aims to predict the listener's facial reactions. The challenge lies in capturing the relevance between video and audio while balancing appropriateness, realism, and diversity. While prior works have mostly focused on uni-modal inputs or simplified reaction mappings, recent approaches such as PerFRDiff have explored multi-modal inputs and the one-to-many nature of appropriate reaction mappings. In this work, we propose the Facial Reaction Diffusion (ReactDiff) framework that uniquely integrates a Multi-Modality Transformer with conditional diffusion in the latent space for enhanced reaction generation. Unlike existing methods, ReactDiff leverages intra- and inter-class attention for fine-grained multi-modal interaction, while the latent diffusion process between the encoder and decoder enables diverse yet contextually appropriate outputs. Experimental results demonstrate that ReactDiff significantly outperforms existing approaches, achieving a facial reaction correlation of 0.26 and diversity score of 0.094 while maintaining competitive realism. The code is open-sourced at \href{https://github.com/Hunan-Tiger/ReactDiff}{github}.