Knowledge catalogue
arXiv:2605.24137v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to generate summaries of software bug reports, including sections such as Steps-to-Reproduce (S2R),
arXiv:2510.01384v4 Announce Type: replace Abstract: A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Model
arXiv:2605.26097v1 Announce Type: new Abstract: Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required repla
arXiv:2605.24370v1 Announce Type: new Abstract: Behavioral phenotyping of genetic animal models currently requires labor-intensive manual feature engineering that limits reproducibility and scalabilit
arXiv:2603.06626v2 Announce Type: replace-cross Abstract: Traditional Mixture-of-Experts (MoE) training typically proceeds without any structural priors, effectively requiring the model to simultaneou
arXiv:2605.24042v1 Announce Type: cross Abstract: Of 1{,}536 Gaussian release covariances we tested for single-layer hidden-state privacy, zero achieve both moderate utility and moderate privacy again
arXiv:2605.25203v1 Announce Type: cross Abstract: We apply the influence-adaptive Walsh geometry of a companion theory paper (arXiv:2605.01637) to extreme low-bit weight-only LLM quantization. The rec
arXiv:2512.05865v5 Announce Type: replace-cross Abstract: We introduce a simple post-training method that makes transformer attention sparse without sacrificing performance. Applying a flexible sparsi
arXiv:2605.25267v1 Announce Type: cross Abstract: Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cos
arXiv:2605.26012v1 Announce Type: cross Abstract: Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value an
arXiv:2605.23960v1 Announce Type: cross Abstract: Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuri
arXiv:2605.24417v1 Announce Type: new Abstract: Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data
arXiv:2605.24869v1 Announce Type: new Abstract: Sequence modeling requires both compositional reasoning and local static knowledge retrieval, yet standard Transformers handle both through dense comput
arXiv:2605.26004v1 Announce Type: cross Abstract: Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with
arXiv:2605.24425v1 Announce Type: cross Abstract: The residual update of a pre-norm Transformer layer admits an interpretation as one step of a first-order optimizer acting on a surrogate token energy
arXiv:2605.23961v1 Announce Type: cross Abstract: The design of RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Despite recent pro
arXiv:2605.23993v1 Announce Type: cross Abstract: World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite ra
arXiv:2605.26037v1 Announce Type: new Abstract: We test the standard RLVR tool-use recipe -- GRPO on Qwen2.5-7B-Instruct -- on a deliberately minimal knowledge-graph tool API: four Freebase navigation
arXiv:2605.24590v1 Announce Type: cross Abstract: Low-light, long-exposure defocus deblurring remains a challenging problem due to the simultaneous presence of severe blur and complex biased noise. Ex
arXiv:2605.24428v1 Announce Type: new Abstract: Stochastic process-based molecular graph generators have become the state of the art for template-free single-step retrosynthesis. However, these models
arXiv:2605.24371v1 Announce Type: cross Abstract: CT report generation (CTRG) requires models to summarize three-dimensional anatomical context and pathological findings from hundreds of axial slices.
arXiv:2605.25488v1 Announce Type: cross Abstract: Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, m
arXiv:2605.25928v1 Announce Type: new Abstract: We describe the winning system for Task 2 of the KSAA-2026 Shared Task on Arabic Speech Dictation with Automatic Diacritization. The task requires produ
arXiv:2605.24846v1 Announce Type: cross Abstract: Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently un
arXiv:2605.25046v1 Announce Type: cross Abstract: YOLO-series and DETR-based detectors struggle with tiny-object detection. YOLO-style models benefit from efficient dense prediction, but their large-s
arXiv:2605.25866v1 Announce Type: new Abstract: Accurately predicting crystal properties is critical for accelerating materials discovery, but it is often limited by scarce labeled data and costly the
arXiv:2605.25388v1 Announce Type: new Abstract: Nucleotide sequences constitute the fundamental genetic basis of biological systems, rendering viral genomic analysis critical for biomedical advancemen
arXiv:2605.25629v1 Announce Type: new Abstract: Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train--t
arXiv:2605.22972v1 Announce Type: cross Abstract: Humans, animals, and modern machine learning models exhibit impressive abilities to learn complex behaviors and generalize these behaviors to unseen s
arXiv:2602.11146v2 Announce Type: replace-cross Abstract: Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computatio
arXiv:2602.18788v3 Announce Type: replace Abstract: We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP
arXiv:2605.23893v1 Announce Type: new Abstract: We propose Complete-muE, a framework which targets hyperparameter transfer across dense FFN and any Mixture-of-Experts (MoE) setups in transformer block
arXiv:2605.23178v1 Announce Type: new Abstract: Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scen
arXiv:2605.23610v1 Announce Type: cross Abstract: Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific
arXiv:2605.23118v1 Announce Type: cross Abstract: Tracking tumor lesions across serial CT scans is essential for oncological response assessment. Existing automated methods face a fundamental trade-of
arXiv:2605.23428v1 Announce Type: new Abstract: In modern multimedia systems, efficient video processing is critical, especially in resource-constrained environments such as IoT-based camera networks,
arXiv:2605.22882v1 Announce Type: new Abstract: Video world models can generate realistic futures from a single instruction, but they often fail to preserve consistent point-level motion over time. As
arXiv:2605.23903v1 Announce Type: new Abstract: Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rel
arXiv:2605.23482v1 Announce Type: cross Abstract: Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increas
arXiv:2511.11051v3 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) fusion enables the composition of subject and style representations for controllable generation without retraining. Howev
arXiv:2605.23194v1 Announce Type: cross Abstract: Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either fla
arXiv:2605.23345v1 Announce Type: new Abstract: Interactive world models for first-person shooter (FPS) games must resolve high-frequency overlapping control signals at every frame without disrupting
arXiv:2605.23872v1 Announce Type: new Abstract: We introduce training-free looped transformers, in which a lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen c
arXiv:2601.00969v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models provide strong action priors for robotic manipulation, but their reactive behavior can fail under distribu
arXiv:2605.23518v1 Announce Type: new Abstract: Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in m
arXiv:2605.22341v1 Announce Type: new Abstract: Hard-label classification is usually trained with smooth surrogate losses, most prominently softmax cross-entropy. We isolate an asymptotic mechanism by
arXiv:2605.22432v1 Announce Type: new Abstract: Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent works challenge both components: Schedule-Free optimiz
arXiv:2511.18159v2 Announce Type: replace Abstract: Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training var
arXiv:2605.22221v1 Announce Type: new Abstract: Backtracking search underlies classical constraint solvers, planners, and theorem provers. Recent transformer-based reasoning systems explore search tre
arXiv:2605.22401v1 Announce Type: new Abstract: Does the relationship between learning rules and brain alignment generalize across species? We extend our prior finding that untrained CNNs match backpr
arXiv:2605.22531v1 Announce Type: new Abstract: There is a gap between the theoretical foundations of disentanglement and the practice of modern representation learning. Existing theoretical framework
arXiv:2605.22338v1 Announce Type: new Abstract: Reconstructing continuous physical fields from sparse measurements is a central inverse problem, but data-driven generative models can produce states th
arXiv:2604.02889v2 Announce Type: replace-cross Abstract: Data assimilation is the process of estimating the state of a dynamical system over time by combining model predictions with measurements. Thi
arXiv:2605.22183v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures m
arXiv:2605.21766v1 Announce Type: new Abstract: Being able to relight human performance is a fundamental task for post production and content creation. We present BodyReLux, a subject-specific video d
arXiv:2605.22005v1 Announce Type: cross Abstract: We show that singular value decomposition of the lm_head} weight matrix of a transformer-based large language model -- requiring only five lines of Py
arXiv:2605.22679v1 Announce Type: new Abstract: Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract in
arXiv:2605.21854v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.g. OpenVLA) and co
arXiv:2605.20690v1 Announce Type: new Abstract: Agentic discovery has shown that LLM-driven search can find novel algorithms, designs, and code under benchmark conditions. Translating the paradigm to
arXiv:2605.22777v1 Announce Type: new Abstract: Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations th