Related papers: Representation Without Reward: A JEPA Audit for LL…

Large language models (LLMs) can be adapted to new tasks using parameter-efficient fine-tuning (PEFT) methods that modify only a small number of trainable parameters, often through low-rank updates. In this work, we adopt a…

AI text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary. On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834…

Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel method that operates on the hidden representations of a PLM to…

We propose WirelessJEPA, a novel wireless foundation model (WFM) that uses the Joint Embedding Predictive Architecture (JEPA). WirelessJEPA learns general-purpose representations directly from real-world multi-antenna IQ data by predicting…

We study whether 3D self-supervised pretraining with Point--JEPA enables label-efficient grasp joint-angle prediction. Meshes are sampled to point clouds and tokenized; a ShapeNet-pretrained Point--JEPA encoder feeds a $K{=}5$…

Fine-tuning large language models (LLMs) is computationally intensive because it requires updating all parameters. Low-Rank Adaptation (LoRA) improves efficiency by modifying only a subset of weights but introduces a trade-off between…

Recent advances in large language models (LLMs) have significantly enhanced question-answering (QA) capabilities, particularly in open-domain contexts. However, in closed-domain scenarios such as education, healthcare, and law, users demand…

Future wireless systems increasingly require predictive and transferable representations that can support multiple physical-layer (PHY) tasks under dynamic environments. However, most existing supervised learning-based methods are designed…

Autoregressive large language models (LLMs) are bottlenecked by sequential decoding, where each new token typically requires executing all transformer layers. Existing dynamic-depth and layer-skipping methods reduce this cost, but often…

Unified representation learning for multi-source data integration faces two important challenges: blockwise missingness and blockwise signal heterogeneity. The former arises from sources observing different, yet potentially overlapping,…

Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on trivially recoverable encodings. We formalize payload recoverability via classifier accuracy and…

Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but might result in modality collapse. To alleviate such issues,…

This paper introduces a novel application of Video Joint-Embedding Predictive Architectures (V-JEPAs) for Facial Expression Recognition (FER). Departing from conventional pre-training methods for video understanding that rely on pixel-level…

Recent advances in machine learning (ML) have shown promise in accelerating the discovery of polymers with desired properties by aiding in tasks such as virtual screening via property prediction. However, progress in polymer ML is hampered…

Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize…

A primary function of back-propagation is to compute both the gradient of hidden representations and parameters for optimization with gradient descent. Training large models requires high computational costs due to their vast parameter…

Despite their exceptional performance on various tasks after fine-tuning, pre-trained language models (PLMs) face significant challenges due to growing privacy concerns with data in centralized training methods. We consider federated…

A central question in computational neuroscience is whether the learning rule used to train a neural network determines how well its internal representations align with those of the human visual cortex. We present a systematic comparison of…

Due to their substantial sizes, large language models (LLMs) are typically deployed within a single-backbone multi-tenant framework. In this setup, a single instance of an LLM backbone must cater to multiple users or tasks through the…

Adapting large language models to multiple tasks can cause cross-skill interference, where improvements for one skill degrade another. While methods such as LoRA impose orthogonality constraints at the weight level, they do not fully…