Knowledge catalogue
arXiv:2609.33147v1 Announce Type: new Abstract: Federated low-rank adaptation (LoRA) enables collaborative fine-tuning of large language models without centralizing private client data. Its factorized
On September 29, 2026, Twitter user Severin Field (@sevdeawesome) posted that an AI‑generated video from Claude 5.5 Opus responding to the phrase “AI is a normal technology” was the best AI‑created vi
arXiv:2607.17568v2 Announce Type: replace Abstract: Resource-constrained deployment requires sustaining large language model (LLM) capabilities as models scale under fixed memory and computation budge
arXiv:2609.33807v1 Announce Type: new Abstract: How well can general-purpose multimodal models turn visual understanding and reasoning into embodied manipulation via executable code? We introduce Code
arXiv:2609.34749v1 Announce Type: new Abstract: Real-world driving is inherently multi-agent, yet most existing driving world models generate observations from a single ego vehicle. Independently exte
arXiv:2609.33754v1 Announce Type: new Abstract: Organizations seek analytical value from AI, yet relevant data are often fragmented across organizations and constrained by privacy. This is acute in fi
arXiv:2609.32935v1 Announce Type: new Abstract: Multi-human multi-robot (MH-MR) teams combine robotic autonomy with human expertise, but effective task allocation requires coordinating scarce, dynamic
arXiv:2609.34348v1 Announce Type: new Abstract: Gradient updates on different data generally do not commute: training a language model on two data sources in opposite orders gives different weights, e
arXiv:2609.32566v1 Announce Type: new Abstract: Intelligence is defined in many ways. One of these definitions defines intelligence as the pursuit of learnable novelty. However, learnable novelty can
arXiv:2609.34585v1 Announce Type: new Abstract: We propose Tiny Recursive Models for Combinatorial Optimization (ours{}), a general neural method for combinatorial optimization that scales both depth
arXiv:2603.08309v3 Announce Type: replace Abstract: Vision Transformers (ViTs) often degrade under distribution shifts because they rely on spurious correlations, such as background cues, rather than
arXiv:2607.18574v2 Announce Type: replace Abstract: Direct feedback alignment (DFA) trains hidden layers with fixed random projections of the output error. Even when this feedback provides useful cred
As query traffic grows, so does the compute bill for embedding it. On a low-power device, a large model may not fit in memory. A smaller query model could reduce that cost, but switching usually means
arXiv:2609.33810v1 Announce Type: cross Abstract: Autoregressive text-to-speech (TTS) systems synthesize natural speech but, once trained, offer little control over speaking rate. We show that speakin
arXiv:2609.34807v1 Announce Type: new Abstract: Spatially conditioned diffusion models can embed words and contours in natural-looking images, but vision-language models (VLMs) may fail to recognize t
arXiv:2502.02332v3 Announce Type: replace-cross Abstract: We study task selection to enhance sample efficiency in model-agnostic meta-reinforcement learning (MAML-RL). Traditional meta-RL typically as
arXiv:2609.33566v1 Announce Type: new Abstract: Time series forecasting requires extrapolating the dynamics of an observed process beyond the last available measurement. Yet recurrent forecasting mode
arXiv:2609.34581v1 Announce Type: new Abstract: Temporal video grounding is a key capability of advanced Multimodal Large Language Models (MLLMs) for the thorough understanding of video events, which
arXiv:2609.35082v1 Announce Type: new Abstract: Group-based reinforcement learning such as GRPO trains LLM agents by comparing rollouts sampled for each task, without a learned critic. In long-horizon
arXiv:2609.32781v1 Announce Type: new Abstract: Diffusion vision-language models generate answers by gradually resolving masked tokens, making accurate conditional prediction in partially resolved sta
arXiv:2609.31873v1 Announce Type: new Abstract: Keyframe selection (KFS) has long produced compact video summaries for browsing and retrieval, and representative frames for thumbnails. More recently,
arXiv:2511.11286v3 Announce Type: replace Abstract: Out-of-domain (OOD) robustness is challenging to achieve in real-world computer vision, especially in unsupervised domain adaptation scenarios, wher
arXiv:2609.33110v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs) provide a framework for learning compact representations without directly reconstructing high-dimension
arXiv:2609.35362v1 Announce Type: new Abstract: Large language models (LLMs) typically generate text autoregressively (AR), predicting one token at a time. Block diffusion language models (dLLMs) inst
arXiv:2609.34792v1 Announce Type: new Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-action (VL
arXiv:2609.34720v1 Announce Type: new Abstract: As image generation and editing technologies have progressed substantially, facial forgeries pose significant challenges to privacy and public safety. D
arXiv:2609.33836v1 Announce Type: cross Abstract: Construction environments evolve continuously, causing large geometric changes that degrade static mapping and registration performance. This necessit
arXiv:2609.32027v1 Announce Type: new Abstract: When several surfaces are visible along a ray, recovering visible 3D structure from one image requires jointly estimating their presence and metric dept
arXiv:2609.32534v1 Announce Type: new Abstract: Depth is a natural way to increase the computational capacity in Transformers, yet the contribution of deeper layers can diminish as depth grows larger.
arXiv:2609.35022v1 Announce Type: new Abstract: The integration of deep learning models into image preprocessing pipelines such as super-resolution introduces a largely unexplored attack vector for ad
arXiv:2609.32363v1 Announce Type: new Abstract: Probabilistic time series forecasting requires modeling and predicting complex and time-varying distributions. Recently, Denoising Diffusion Probabilist
arXiv:2609.33803v1 Announce Type: new Abstract: Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate or to a di
arXiv:2510.17611v3 Announce Type: replace Abstract: Unsupervised anomaly detection (UAD) has evolved from specialized single-class models to unified multi-class models, yet existing multi-class models
arXiv:2603.18257v3 Announce Type: replace Abstract: When an RL agent's observations contain distractors driven by the same confounders as its true state, observational data alone cannot identify which
arXiv:2609.34629v1 Announce Type: new Abstract: Many complex systems are observed only through temporally unpaired distribution snapshots, making trajectory-based dynamical learning difficult without
arXiv:2609.32663v1 Announce Type: new Abstract: The memory usage and decoding latency of LLM inference grow rapidly with context length. To reduce these costs, key-value (KV) cache compression methods
arXiv:2609.34408v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have shown strong promise for multimodal reasoning, yet often struggle with tasks requiring concepts beyond what is
arXiv:2609.34503v1 Announce Type: new Abstract: Parameter-efficient adaptation enables continual learners to acquire task-specific knowledge through compact model updates while maintaining strong with
arXiv:2609.34838v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student agents through teacher supervision on their own interactions with an environment. However, in asynchronous m
arXiv:2609.33791v1 Announce Type: new Abstract: Since the advent of knowledge distillation, KL divergence has been the standard loss in distillation. Recently, on-policy distillation (OPD) has emerged
arXiv:2609.31680v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representatio
arXiv:2609.32525v1 Announce Type: new Abstract: The widely used Transolver family of neural operators is based on physics-attention, which softly assigns the points of an unstructured mesh to a small
arXiv:2602.08847v2 Announce Type: replace Abstract: Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for s
arXiv:2609.35106v1 Announce Type: new Abstract: Predicting cellular responses to perturbations is a central problem in cellular biology, with broad applications in systems biology and drug discovery.
arXiv:2609.33530v1 Announce Type: cross Abstract: Natural Language Understanding (NLU) plays a crucial role in various applications, yet its performance suffers from weaknesses in handling the complex
arXiv:2609.35099v1 Announce Type: new Abstract: We present e3j, a fast Euclid-equivariance backend for geometric deep learning applications with JAX bindings for GPU and TPU. Leveraging both optimized
arXiv:2609.32929v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) are widely used for representation learning on graphs, but most methods assume static topologies, making them inefficient o
arXiv:2609.35622v1 Announce Type: cross Abstract: We study two-arm contextual bandits with arm-specific single indices and a shared unknown monotone link. Monotonicity makes the optimal action depend
arXiv:2609.34178v1 Announce Type: new Abstract: Video text editing aims to replace or add text in a video while keeping the rest of the video unchanged, which requires the edited text to be correct in
arXiv:2609.31657v1 Announce Type: new Abstract: Remote-sensing foundation models offer strong representations for SAR imagery, but their behavior under severe long-tail class imbalance is still not we
arXiv:2601.22944v3 Announce Type: replace Abstract: Out-of-distribution generalization becomes challenging when spurious correlations vary across environments while difficult or underrepresented sampl
arXiv:2609.32661v1 Announce Type: new Abstract: Maximum common edge subgraph (MCES) matching finds a partial vertex correspondence between two labeled graphs that preserves as many labeled edges as po
arXiv:2609.35614v1 Announce Type: new Abstract: Adam and its variants dominate neural network training, but a single run only reveals whether a configuration works well after most of its budget is spe
arXiv:2609.35616v1 Announce Type: new Abstract: Interactive 3D head generation requires coordinated speaking and listening motion that responds to an evolving conversation. Existing generators use inc
arXiv:2603.20212v2 Announce Type: replace-cross Abstract: Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Re
arXiv:2609.33887v1 Announce Type: cross Abstract: Block-diffusion language models are served at hand-picked operating points, such as acceptance thresholds, buffer depth, schedule, checkpoint and prec
arXiv:2609.32980v1 Announce Type: new Abstract: Graph reconstruction from partial observations often comes with structural side information, such as degree bounds, triangle counts, or an edge-density
arXiv:2609.32790v1 Announce Type: new Abstract: Task-wise federated multi-objective optimization (FedMOO) trains a shared model for competing prediction objectives under heterogeneous data, partial pa
arXiv:2609.32353v1 Announce Type: new Abstract: Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extremely
arXiv:2609.33582v1 Announce Type: new Abstract: Recent real-world image super-resolution (SR) methods often adapt text-to-image (T2I) backbones with ControlNet-style branches or spatial conditioning t