Self-Distillation Enables Continual Learning
arXiv:2601.19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for
Knowledge catalogue
arXiv:2601.19897v2 Announce Type: replace Abstract: Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for
arXiv:2606.19079v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning (PEFT) has led to model ecosystems in which a single backbone is paired with many task-specialized adapters. Given s
arXiv:2608.06409v1 Announce Type: cross Abstract: Speech language models are increasingly evaluated on paralinguistic tasks by the accuracy of prompted answers, but answer accuracy combines failures a
arXiv:2608.07188v1 Announce Type: new Abstract: SetEasy optimizes classroom engagement in fixed seating grids. It fuses multimodal sensing (wristband physiology, 4K video, environmental data) and trai
arXiv:2608.06632v1 Announce Type: new Abstract: Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., cl
arXiv:2608.06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements. When one call must return many verdicts, some decisions become we
arXiv:2608.06802v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend str
arXiv:2608.07468v1 Announce Type: new Abstract: World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods requir
arXiv:2608.07222v1 Announce Type: new Abstract: Neural scaling laws are foundational for language model development, yet standard formulations systematically under- and overestimate loss at data-scarc
arXiv:2608.06880v1 Announce Type: new Abstract: General-purpose skills promise reusable procedural knowledge for language agents, yet semantic relevance does not guarantee execution utility: a retriev
arXiv:2608.06891v1 Announce Type: new Abstract: Agent skills provide reusable procedural knowledge that helps agents solve specialized tasks. As their use expands, evaluating skill quality becomes inc
arXiv:2608.07449v1 Announce Type: new Abstract: LLM agents increasingly adapt to recurring tasks by accumulating procedural knowledge in skills. These skills are lightweight, reusable textual artifact
arXiv:2608.07382v1 Announce Type: new Abstract: Satellite object detection is challenged by small targets and wide-format scenes that lose detail under standard square-input resizing. We introduce Sky
arXiv:2608.06612v1 Announce Type: cross Abstract: The plethora of readily available geospatial data offers exciting opportunities to learn high quality representations of the planet, but the sheer siz
arXiv:2608.06441v1 Announce Type: new Abstract: Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular inter-node embedding exchanges. We pre
arXiv:2509.00559v3 Announce Type: replace Abstract: Humans intuitively navigate social interactions by simulating unspoken dynamics and reasoning about others' perspectives, even with limited informat
arXiv:2608.07063v1 Announce Type: cross Abstract: Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images. H
arXiv:2608.06741v1 Announce Type: new Abstract: Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales. For equilibrium reasoni
arXiv:2608.06650v1 Announce Type: cross Abstract: Reduced-order models based on Cosserat-rod theory are now well established, and modeling theory is no longer the primary bottleneck in soft-robot cont
arXiv:2603.21638v2 Announce Type: replace Abstract: Event cameras excel at detecting small, fast drones, but today's detectors give away their key advantage: they convert the sparse event stream into
arXiv:2608.06907v1 Announce Type: new Abstract: Legged robots require robust agility to perceive and interact with complex and dynamic environments within a constrained time. However, most existing qu
arXiv:2510.09904v2 Announce Type: replace-cross Abstract: Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stabili
arXiv:2608.07014v1 Announce Type: new Abstract: Aggregate scaling curves suggest that Video LLMs improve smoothly or saturate as visual budgets grow. We show that this view can conceal large, opposing
arXiv:2608.06477v1 Announce Type: cross Abstract: Computer-use agents (CUAs) face a growing threat from indirect prompt injection, where adversarial instructions are planted in the environment such as
arXiv:2608.07224v1 Announce Type: new Abstract: Motivated by LLMs, which generate outputs by iteratively sampling from next-token distributions, we introduce a PAC-learning model for binary stochastic
arXiv:2608.06758v1 Announce Type: new Abstract: We present Stockmark-Nemotron-3-Nano-Omni-JapanDocReader, a Japanese document understanding model built from Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
arXiv:2608.07249v1 Announce Type: new Abstract: We introduce Stoicheia, a 405M-parameter character-level masked-diffusion encoder for Ancient Greek whose input factors into five aligned, independently
arXiv:2608.07454v1 Announce Type: cross Abstract: The total synthesis of a complex molecule is among the most demanding intellectual and experimental feats in chemistry: a chemist must plan many steps
arXiv:2608.06946v1 Announce Type: cross Abstract: In gossip learning, a network of nodes trains a shared model collaboratively, without a central coordinator, by repeatedly exchanging parts of their l
arXiv:2608.06762v1 Announce Type: new Abstract: Bisimulation metrics quantify behavioral similarity in Markov decision processes, but their Wasserstein fixed-point operator updates every state pair an
arXiv:2608.06408v1 Announce Type: cross Abstract: Audio-driven 3D facial animation aims to synthesize realistic and temporally coherent motions from speech. Despite notable progress in lip synchroniza
arXiv:2608.06959v1 Announce Type: new Abstract: Modern Earth observation (EO) satellites carry increasingly advanced sensors that produce vast volumes of high-resolution, multispectral data, yet downl
arXiv:2608.06712v1 Announce Type: new Abstract: Model robustness against natural image corruptions is essential for safety-critical applications. While existing methods primarily focus on implicit rep
arXiv:2608.06770v1 Announce Type: new Abstract: Controllable surgical world models can provide a generative foundation for surgical artificial intelligence and simulation by synthesizing realistic ins
arXiv:2509.05208v2 Announce Type: replace Abstract: Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise vis
arXiv:2608.06587v1 Announce Type: cross Abstract: Robot swarms utilize many independent limited-sensing agents to produce complex emergent behaviors without requiring centralized control. However, lit
arXiv:2608.07106v1 Announce Type: new Abstract: Deploying three-dimensional deep learning frameworks to low-power embedded processors is bottlenecked by the unstructured nature of spatial data and the
arXiv:2608.06672v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a robust architecture for grounding large language models (LLMs) in trusted knowledge. However, standard
arXiv:2608.06512v1 Announce Type: new Abstract: Randomized experiments are often run in one population to guide decisions in another. Allocating by experimental proportions wastes budget on groups tha
arXiv:2608.06544v1 Announce Type: new Abstract: World models for visual control typically learn compact latent states by reconstructing observations, implicitly encouraging representations to preserve
arXiv:2608.07446v1 Announce Type: cross Abstract: Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI app
arXiv:2608.07314v1 Announce Type: cross Abstract: Vision-language-action (VLA) models are commonly adapted to downstream manipulation tasks via supervised fine-tuning (SFT) or online reinforcement lea
arXiv:2608.07043v1 Announce Type: cross Abstract: Developing nonlinear models that are both expressive and computationally efficient remains a challenge in machine learning and nonlinear system identi
arXiv:2608.07429v1 Announce Type: new Abstract: Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability proble
arXiv:2608.06467v1 Announce Type: new Abstract: Facial expression recognition (FER) in videos is challenging because models must identify subtle, temporally evolving affective states that vary across
arXiv:2608.06396v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models route each token through a small subset of experts, making routing patterns useful for identifying task-relev
arXiv:2608.06663v1 Announce Type: new Abstract: Frontier language models solve reasoning problems in a single forward pass that would have been research contributions years ago, yet fail at multi-hour
arXiv:2608.06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits
arXiv:2606.15485v2 Announce Type: replace-cross Abstract: Agentic AI systems act autonomously, use tools, adapt to context, and operate in complex real-world environments. However, these same characte
arXiv:2608.06630v1 Announce Type: new Abstract: Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We
arXiv:2608.06563v1 Announce Type: new Abstract: Machine learning and optimization have advanced together, with practical demands motivating new theory and theoretical breakthroughs enabling new applic
arXiv:2603.27723v2 Announce Type: replace Abstract: Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-c
arXiv:2608.07274v1 Announce Type: cross Abstract: Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead. However, its split architectur
arXiv:2608.07214v1 Announce Type: cross Abstract: Modern AI is no longer a single model but an ecosystem: classical ML predictors, deep and multimodal models, large language models, and agents, each t
arXiv:2608.06503v1 Announce Type: new Abstract: Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary e
arXiv:2608.06599v1 Announce Type: new Abstract: Mandibular reconstruction restores facial continuity and oral function after segmental resection. Patient-specific cutting guides transfer a computed to
arXiv:2403.00802v2 Announce Type: replace-cross Abstract: Production-grade recommender systems rely heavily on a large-scale corpus used by online media services, including Netflix, Pinterest, and Ama
arXiv:2608.07317v1 Announce Type: cross Abstract: The AI-Native Manifesto envisions large-scale agile software development in which humans increasingly govern intent, risk, and exceptions while agents
arXiv:2608.06394v1 Announce Type: new Abstract: Multi-label node classification is an important yet challenging task in graph learning, where nodes exhibit multiple semantics simultaneously. Existing
arXiv:2608.06657v1 Announce Type: new Abstract: Modern cyber-physical and AI-assisted systems couple human operators, AI decision modules, and automated controllers in a single control loop, so trustw