Knowledge catalogue
arXiv:2609.33432v1 Announce Type: new Abstract: Manual dense annotation remains a major obstacle to deploying semantic segmentation models in new driving environments. Active domain adaptation (ADA) s
arXiv:2609.34975v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) improves language-model reasoning by comparing verified rewards among multiple solution rollouts for each quer
arXiv:2609.33200v1 Announce Type: new Abstract: On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with acc
arXiv:2609.35319v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own trajectories with dense teacher supervision. Recent work on OPD for multi-turn autonomous agent
arXiv:2609.35065v1 Announce Type: cross Abstract: Reusable prefix key-value (KV) caches can outgrow GPU memory in large language model (LLM) serving. A memory-semantic flash hierarchy offers SSD-backe
arXiv:2609.31654v1 Announce Type: new Abstract: Video diffusion transformers depend on temporal attention to coordinate information across frames, yet nearly everything known about this mechanism come
arXiv:2609.35219v1 Announce Type: new Abstract: Relational deep learning models database rows and foreign-key links as a heterogeneous graph for prediction from record attributes and relational contex
arXiv:2609.34596v1 Announce Type: new Abstract: Rapid and accurate burn scar delineation from satellite imagery is essential for post-fire damage assessment. Sentinel-3 OLCI, with daily revisit and 21
arXiv:2609.31881v1 Announce Type: new Abstract: Dynamic text-attributed graphs (DTAGs), where nodes, edges, and textual attributes evolve over time, are crucial in applications such as social networks
arXiv:2609.33548v1 Announce Type: new Abstract: Fine-tuning anguage models (LLMs) with first-order optimizers requires a memory several times larger than that required for inference. Memory-efficient
arXiv:2609.33567v1 Announce Type: cross Abstract: Structured quantum-state learning not only depends on an expressive ansatz but also on an operational certificate that stays meaningful with finite me
arXiv:2609.35493v1 Announce Type: new Abstract: Autonomous planetary exploration requires robots to navigate unknown, uneven terrain while assessing risk, traversability, and energetic cost. Quadruped
arXiv:2609.33937v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) and Generalized Category Discovery (GCD) are traditionally treated as disjoint problems: the former adapts models to domain s
arXiv:2609.33982v1 Announce Type: cross Abstract: Spatial reasoning is fundamental to general robot intelligence, as it enables robots to complete long-horizon tasks involving multi-object interaction
arXiv:2609.35465v1 Announce Type: new Abstract: Leech-lattice quantization gives good quality at two bits per weight, but its codebooks hold more than 10^14 points, too many for a lookup table. Our ea
arXiv:2609.34319v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models enable generalizable robotic control but remain computationally expensive. Token caching provides a training-free, p
arXiv:2609.33589v1 Announce Type: new Abstract: Efficient exploration often remains a central bottleneck in reinforcement learning with verifiable rewards (RLVR). Although temperature control and test
arXiv:2609.34343v1 Announce Type: new Abstract: Dataset distillation compresses a training set into a small synthetic set, usually evaluated one at a time. In federated and data-governance settings, s
arXiv:2609.33499v1 Announce Type: new Abstract: What information is needed to turn a natural-gradient direction into a useful finite update? Under a population Kullback-Leibler (KL) budget, we call a
arXiv:2511.20104v2 Announce Type: replace Abstract: Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed 'emergent
arXiv:2609.34106v1 Announce Type: new Abstract: Large visual foundation models have demonstrated remarkable transferability across a wide range of downstream tasks. To deploy such models efficiently,
arXiv:2609.34074v1 Announce Type: cross Abstract: In school choice, a lottery number is often used by the matching mechanism to break ties when there are more students who prefer the same school than
arXiv:2609.31747v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) must balance local detail against scene context when interpreting ultra-high-resolution (UHR) remote sensing (R
arXiv:2603.19198v2 Announce Type: replace-cross Abstract: We introduce the exponentially weighted signature (EWS), a continuous-time model that computes iterated integrals of a path, where each increm
arXiv:2609.32759v1 Announce Type: new Abstract: We introduce the Extender, a log-structured variant of the standard Transformer architecture. In a standard Transformer, each layer communicates with su
arXiv:2609.32927v1 Announce Type: new Abstract: Transformer-based language models perform well on symbolic tasks, yet it remains unclear whether they learn generalizable rules or rely on statistical s
arXiv:2609.32679v1 Announce Type: cross Abstract: GUI World Models (GUI-WMs) are increasingly used to predict future states for agent planning and simulation, yet most existing formulations condition
arXiv:2609.35684v1 Announce Type: cross Abstract: With the recent advancements of neural compressors, explicitly incorporating perception constraints into the design of compression schemes has gained
arXiv:2609.35392v1 Announce Type: new Abstract: Adam is the default optimizer for training modern deep neural networks, yet its adaptive behavior remains poorly understood due to the complex interacti
arXiv:2609.32934v1 Announce Type: new Abstract: Neural network training is inherently stochastic, with factors such as weight initialization leading to distinct models despite comparable predictive pe
arXiv:2609.32196v1 Announce Type: cross Abstract: Language models are now routinely graded by other language models. If post-training makes a model's own writing more predictable, it may also teach th
arXiv:2609.32942v1 Announce Type: cross Abstract: A two-hop question makes a language model retrieve twice: once to produce a bridge entity, and once to retrieve with it. Transformers resolve that ent
arXiv:2609.33078v1 Announce Type: new Abstract: Automatic differentiation (AD) lets neural networks compute derivatives of governing equations to machine precision, and this precision has made it the
arXiv:2609.34599v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, yet how RL reshapes these policies remains poorly un
arXiv:2609.34590v1 Announce Type: cross Abstract: Language models often process long inputs sequentially in chunks, but continuing to read after sufficient evidence has been acquired wastes computatio
arXiv:2509.19453v2 Announce Type: replace-cross Abstract: We investigate when foundation models converge towards shared representations, and how this convergence depends on model capacity, training re
arXiv:2609.33240v1 Announce Type: new Abstract: The Forward-Forward Algorithm (FFA) replaces backpropagation (BP) with layer-wise local contrastive objectives, eliminating the backward pass and the ne
arXiv:2609.33597v1 Announce Type: cross Abstract: Side-channel evaluators routinely inspect leakage tests while acquisition is still running, and extend or stop the campaign based on what they see. Fi
arXiv:2609.33985v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) is widely used to adapt large language models to downstream tasks. Crowdsourcing user conversations is an established app
arXiv:2609.33370v1 Announce Type: new Abstract: Open-set graph anomaly detection trains on a few labeled anomalies from one class and must also find anomaly classes that were never labeled. Published
arXiv:2609.33291v1 Announce Type: cross Abstract: Many generative systems return multiple candidate responses and are evaluated according to the best one. Recent work shows that, when demonstrations a
arXiv:2609.34050v1 Announce Type: cross Abstract: What determines the unavoidable sample cost of learning cyclic causal structure? For cyclic linear non-Gaussian models, we study exact condensation re
arXiv:2607.14246v2 Announce Type: replace-cross Abstract: Generative models are steered with knobs -- prompts, guidance scales, property tags. Turn one as hard as you like and, past a point, it stops
arXiv:2609.31684v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) introduces a specific failure mode in discrete diffusion language models: when retrieved context contradicts para
arXiv:2609.33280v1 Announce Type: cross Abstract: Medical images are released with the reports that describe them, and protecting the image does not protect the report. This paper measures the text co
arXiv:2609.35035v1 Announce Type: new Abstract: The integration of artificial intelligence into computer-aided design frameworks has sparked a shift in the design of analog integrated circuits (ICs),
arXiv:2510.15508v2 Announce Type: replace Abstract: In this study, we propose an enhancement to the similarity computation mechanism in multimodal contrastive pretraining frameworks such as CLIP. Prio
arXiv:2609.33715v1 Announce Type: new Abstract: Accurate numerical solutions of partial differential equations (PDEs) are crucial in numerous science and engineering applications. In this work, we int
arXiv:2609.32939v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) are largely homogeneous, as their agents behave alike even across distinct LLMs. We show that
arXiv:2609.32591v1 Announce Type: cross Abstract: Data-driven model predictive control (MPC) combines learned world models with online trajectory optimization, achieving strong performance in continuo
arXiv:2609.33967v1 Announce Type: cross Abstract: Practical assistive and rehabilitative brain--computer interfaces require subject-independent motor-imagery EEG (MI-EEG) decoders that generalize to n
arXiv:2609.35058v1 Announce Type: new Abstract: Effective multi-turn agents require interaction strategies that coordinate information gathering, actions, and feedback over long horizons. GRPO is a re
arXiv:2609.34642v1 Announce Type: new Abstract: Schrodinger bridges provide an entropy-regularized framework and a principled solution for unpaired domain translation. In practice, a pretrained bridge
arXiv:2609.31773v1 Announce Type: new Abstract: We study whether a manually specified runtime supervisor can correct recurring failures of an existing end-to-end parking policy in a fixed CARLA parkin
arXiv:2609.32384v1 Announce Type: new Abstract: Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain offer
arXiv:2609.35143v1 Announce Type: new Abstract: AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we i
arXiv:2609.33157v1 Announce Type: new Abstract: DAgger improves robot policies by aggregating expert supervision from states visited during policy execution. Robot-gated DAgger automates expert querie
arXiv:2609.32665v1 Announce Type: cross Abstract: ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in E
arXiv:2609.34297v1 Announce Type: new Abstract: Language-conditioned robot policies have made clear progress in multitask manipulation, but task-relevant local visual evidence usually stays hidden ins
arXiv:2609.35336v1 Announce Type: cross Abstract: Despite the promise of Large Language Models (LLMs) in computational chemistry, rigorous combinatorial chemistry problems remain difficult because the