49 articles mentioning coder-large
arXiv:2607.11964v1 Announce Type: new Abstract: Autonomous driving requires long-horizon closedloop decision making in dynamic traffic environments. Latent world models offer an effective framework for this problem by enabling imagination-based decision making in compact latent spaces. However, mult
arXiv:2607.12094v1 Announce Type: cross Abstract: Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models. Neural networks often produce overconfident predictions for inputs that deviate from their training data, leading to significant de
arXiv:2501.05396v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in high-stakes decisions such as hiring and college admissions, making their social bias a critical concern. While LLMs are trained to refuse explicitly biased requests, bias can be leaked implicit
arXiv:2607.12380v1 Announce Type: new Abstract: Small molecules, crystals, and proteins all reduce to atoms in 3D space, yet their generative pipelines remain fragmented across domains, each with its Small molecules, crystals, and proteins all reduce to atoms in 3D space, yet their generative pipeli
arXiv:2607.11933v1 Announce Type: new Abstract: Cross-encoders achieve high reranking accuracy in Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment. We address this by fine-tuning LLaMA 3 (8B) as a drop-in reranker using a two-stage p
arXiv:2607.12166v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are the standard for decomposing superposed neural representations into interpretable features, and evaluation relies predominantly on correlational recovery metrics -- cosine similarity between ground-truth directions and de
arXiv:2607.12054v1 Announce Type: cross Abstract: Breast ultrasound is widely used for screening, yet automated analysis remains challenging due to speckle noise, acquisition variability, and weak separation of benign and malignant cases in standard ultrasound imaging. Graph convolutional networks (
arXiv:2606.27321v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) have become a leading tool for interpreting the representations of vision foundation models, decomposing their polysemantic activations into a larger set of sparse, more monosemantic features. The Top-$k$ SAE, a now
arXiv:2606.07882v2 Announce Type: replace-cross Abstract: Different vision neural networks -- trained to classify, contrast, reconstruct, or match images to text -- should have correspondingly different internal representations. We report that they do not. After training, the top sixteen principal d
arXiv:2607.11801v1 Announce Type: cross Abstract: Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content. Improving this without the cost of retraining calls for an effective
arXiv:2602.14687v2 Announce Type: replace-cross Abstract: Improving Sparse Autoencoders (SAEs) requires benchmarks that can precisely validate architectural innovations. Current LLM-based SAE benchmarks are too noisy to differentiate architectural improvements, while commonly used synthetic-data exp
arXiv:2605.21510v2 Announce Type: replace-cross Abstract: Reference-based graph compression encodes each vertex's neighbor list as differences from a nearby encoded list. WebGraph's BVGraph fixes a single encoding pipeline and relies on a separately chosen vertex ordering -- typically URL-lexicograp
arXiv:2607.10285v1 Announce Type: new Abstract: We study how unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables underlying the data-generating process. Without embedding domain knowledge, we mimic a typical discovery
arXiv:2311.00314v2 Announce Type: replace Abstract: Topic modeling has emerged as a valuable tool for discovering patterns and topics within large collections of documents. However, when cross-analysis involves multiple parties, data privacy becomes a critical concern. Federated topic modeling has b
arXiv:2607.10580v1 Announce Type: cross Abstract: AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising. To counter this, res
arXiv:2606.23964v2 Announce Type: replace Abstract: Self-supervised learning in fluorescence microscopy often relies on 2D projections, despite the inherently three-dimensional nature of cells. We present a systematic comparison of 2D and 3D masked autoencoders (MAE-2D vs. MAE-3D) on volumetric micr
arXiv:2511.17113v3 Announce Type: replace-cross Abstract: Network Intrusion Detection Systems (NIDS) are essential tools for detecting network attacks and intrusions. While extensive research has explored the use of supervised Machine Learning for attack detection and characterisation, these methods
arXiv:2607.09122v1 Announce Type: new Abstract: Data-driven methods, including graph neural networks, have been studied for accelerating power flow calculations in recent years, but very little attention has been paid to the solution feasibility, which can be obtained by traditional solvers. This pa
arXiv:2607.08499v1 Announce Type: new Abstract: We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trained BERT models. Cross-seed feature universality is a fundamental challenge in mechanistic interpret
arXiv:2607.07756v1 Announce Type: new Abstract: Multimodal learning usually requires a dedicated encoder per modality. When a tabular modality is involved, prior work has been mostly using a \emph{plain MLP} as the encoder. Yet if it were a strong encoder, the tabular domain would not be ``the last
arXiv:2607.08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept. However, in vision-language models (VLMs), vanill
arXiv:2605.18224v5 Announce Type: replace-cross Abstract: We study exact constant collapse in variational autoencoders: the deterministic encoder mean becomes independent of the input. The prior remains the standard Gaussian. Before VAE training, we select a fixed teacher posterior from a GMM-based
arXiv:2607.01275v1 Announce Type: cross Abstract: Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture the true distribution of latent representations for complex datasets. This mismatch can limit reconst
arXiv:2507.22063v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating vulnera
arXiv:2607.01883v1 Announce Type: new Abstract: Code is the medium through which large language models generate structured artifacts: charts, scientific figures, vector graphics, CAD models, 3D scenes, and hardware designs are all produced by writing programs. In this regime single pass inference is
arXiv:2607.01336v1 Announce Type: cross Abstract: Neural Quantum States (NQS) are a remarkably expressive class of variational ans\"atze for quantum many-body wavefunctions, yet little is understood about their internal mechanisms: trained on variational objectives alone, how do NQS accurately captu
arXiv:2607.01799v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m<n$, and inferring a sparse code $\mat
arXiv:2510.20441v2 Announce Type: replace-cross Abstract: Neural audio codecs have largely promoted the application of language models (LMs) for speech applications. However, the effectiveness of autoregressive LM-based models in unifying speech enhancement (SE) tasks remains underexplored. In this
arXiv:2607.01792v1 Announce Type: new Abstract: While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones. A simple and effective remedy is pro
arXiv:2606.31699v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) have recently been proposed as interpretable tools for concept-level manipulation, under the assumption that isolated features can serve as controllable intervention points. In this work, we systematically evaluate
arXiv:2607.00852v1 Announce Type: cross Abstract: This work studies the hidden-state inversion problem: recovering the original input token sequence of a decoder-only language model from its last-layer hidden states. Rather than treating inversion as a one-shot reconstruction, we study it as a conti
arXiv:2607.00004v1 Announce Type: cross Abstract: While advanced foundation models like ModernBERT significantly outperform older architectures in dense retrieval, they surprisingly lag behind the aging BERT-base baseline in learned sparse retrieval (LSR). We identify the root cause as the \textit{V
arXiv:2607.00023v1 Announce Type: cross Abstract: Dense sentence embeddings are fundamental to modern Retrieval-Augmented Generation (RAG) systems but suffer from a lack of interpretability due to feature superposition. This opacity hinders the alignment of retrieval processes with human intent, as
arXiv:2607.00477v1 Announce Type: new Abstract: A total of seven categorical encoding methods were tested on the IEEE-CIS fraud benchmark dataset (590,540 records, 3.5% positives, 8 high-cardinality columns). The encoders were evaluated using a stratified 5-fold cross-validation (CV) with three repe
arXiv:2606.15054v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) detect features via inner product, so a feature's activation scales with both its directional alignment and the input's norm. Features that fire on token norm therefore claim dictionary slots regardless of content alignme
arXiv:2603.03031v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as a power
arXiv:2606.30648v1 Announce Type: cross Abstract: Causal mediation analysis decomposes a treatment effect into indirect pathways through mediators and direct pathways not operating through them. Modern biomedical studies often involve high-dimensional covariates and mediators that are noisy proxies
arXiv:2606.31570v1 Announce Type: cross Abstract: Masked autoencoding has emerged as a prominent paradigm for self-supervised learning on 3D point clouds, achieving competitive performance across downstream tasks. Unlike its 2D counterpart, 3D masked autoencoding directly reconstructs spatial coordi
arXiv:2606.30336v2 Announce Type: replace Abstract: We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of task-specific decoders. Unlike existing tabular in-context learners, which entangle fea
arXiv:2606.30914v1 Announce Type: new Abstract: Event detection (ED) systems are typically evaluated on clean, curated text, leaving their robustness to real-world noise largely unexplored, particularly for low-resource languages such as Bangla. We introduce a generalized Bangla news event ontology
arXiv:2507.23220v2 Announce Type: replace Abstract: Traditional topic models are effective at uncovering latent themes in large text collections. However, due to their reliance on bag-of-words representations, they struggle to capture semantically abstract features. While some neural variants use ri
arXiv:2606.29102v1 Announce Type: cross Abstract: Jointly learning to segment and classify medical images demands cross-task synergy, yet encoder-sharing architectures limit decoder reconstruction to task-private representations, permanently discarding the boundary cues and semantic priors each bran
arXiv:2412.08108v3 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance on multimodal tasks but remain highly vulnerable to small adversarial perturbations in input images. Existing attacks typically target the vision encoder's final output
arXiv:2509.12159v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models have demonstrated exceptional performance in UI2Code tasks, significantly enhancing website development efficiency. However, these tasks incur substantially higher computational overhead than traditional code
arXiv:2606.28377v1 Announce Type: cross Abstract: HAR using Inertial Measurement Unit (IMU) sensors is vital for healthcare monitoring and rehabilitation. Despite deep learning advancements, major challenges remain: reliance on labeled data, multi-sensor fusion complexity, and the limited ability of
arXiv:2606.30609v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges. Systematic studies reveal pervasive
arXiv:2602.12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level representa
arXiv:2606.22248v2 Announce Type: replace-cross Abstract: Standard autoregressive Transformer decoders can often exhibit substantial forgetting under sequential fine-tuning on shifting curriculum distributions. This technical report evaluates SamatNext v0.2-B, an experimental 356M-parameter hybrid s
arXiv:2606.24147v2 Announce Type: replace-cross Abstract: Aligner-Encoders are recently proposed seq2seq end-to-end ASR models that replace decoder attention by predicting the uth token directly from the u-th encoder position, so the encoder must learn the alignment internally without cross-attentio