Knowledge catalogue
arXiv:2605.11205v1 Announce Type: new Abstract: Benchmark evaluation across AI and safety-critical domains overwhelmingly relies on simple averaging. We demonstrate that this practice produces substan
arXiv:2605.11361v1 Announce Type: new Abstract: Inference-time reward alignment asks how to turn a pre-trained diffusion model with base law p into a sampler that favors a reward r while remaining clo
arXiv:2605.05922v2 Announce Type: replace Abstract: Recent advances in generative video models are increasingly driven by post-training and test-time scaling, both of which critically depend on the qu
arXiv:2605.11574v1 Announce Type: new Abstract: The literature on how large language models handle conflict between their training knowledge and a contradicting document presents a persistent empirica
arXiv:2605.10983v1 Announce Type: cross Abstract: Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from sig
arXiv:2605.12236v1 Announce Type: cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral clon
arXiv:2412.14461v4 Announce Type: replace Abstract: Unstructured text data annotation is foundational to management research. LLMs offer a cost-effective and scalable alternative to human annotation,
arXiv:2605.12288v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences o
arXiv:2605.11473v1 Announce Type: cross Abstract: Soft Actor-Critic (SAC) and its variants dominate Multi-Task Reinforcement Learning (MTRL) due to their off-policy sample efficiency, while on-policy
arXiv:2605.12462v1 Announce Type: cross Abstract: Extreme weather and volatile wholesale electricity markets expose residential consumers to catastrophic financial risks, yet demand response at the di
arXiv:2511.10670v2 Announce Type: replace Abstract: Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing
arXiv:2605.11974v1 Announce Type: new Abstract: Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness lim
arXiv:2602.13004v2 Announce Type: replace Abstract: Granger causality recovers directed interactions from time-series data, but in many distributed systems, the data are vertically partitioned across
arXiv:2605.11993v1 Announce Type: new Abstract: Movie subtitle translation is inherently multimodal, yet text-only systems often miss visual cues needed to convey emotion, action, and social nuance, e
arXiv:2503.16072v4 Announce Type: replace-cross Abstract: Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet mo
arXiv:2605.11380v1 Announce Type: new Abstract: Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stat
arXiv:2605.11744v1 Announce Type: new Abstract: Transformer-based large language models face severe scalability challenges in long-context generation due to the computational and memory costs of full-
arXiv:2605.05971v2 Announce Type: replace Abstract: Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly wit
arXiv:2605.12391v1 Announce Type: cross Abstract: We present a novel method for extracting moving objects from TESS data using machine learning. Our approach uses two stacked 3D U-Nets with skip conne
arXiv:2506.01568v3 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained
arXiv:2605.12312v1 Announce Type: new Abstract: Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true prop
arXiv:2304.10891v2 Announce Type: replace-cross Abstract: Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi
arXiv:2605.12220v1 Announce Type: new Abstract: Safe autonomous agents and mobile robots need fast real time 3D perception, especially for vulnerable road users (VRUs) such as pedestrians. We introduc
arXiv:2605.11020v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classica
arXiv:2605.12380v1 Announce Type: new Abstract: Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fr
arXiv:2605.11735v1 Announce Type: new Abstract: The efficient operation of modern cellular networks hinges on the accurate analysis of spatio-temporal traffic data. Mastering these patterns is essenti
arXiv:2510.03853v4 Announce Type: replace Abstract: We present UGround, a extbf{U}nified visual extbf{Ground}ing paradigm that dynamically selects intermediate layers across extbf{U}nrolled transforme
arXiv:2605.12237v1 Announce Type: new Abstract: Vision-Language Models (VLMs) increasingly operate on ultra-high-resolution (UHR) Earth observation imagery, yet they remain vulnerable to a severe scal
arXiv:2605.11491v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning ability of large language models. How
arXiv:2605.11911v1 Announce Type: new Abstract: Predictive Coding (PC) is an influential account of cortical learning. Much of recent work has focused on comparing PC to Backpropagation (BP) to find w
arXiv:2505.19770v5 Announce Type: replace-cross Abstract: We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and
arXiv:2511.18152v3 Announce Type: replace Abstract: Deep unfolding networks (DUNs) combine the interpretability of model-based methods with the learning ability of deep networks, yet remain limited fo
arXiv:2605.12088v1 Announce Type: new Abstract: Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple refere
arXiv:2605.12169v1 Announce Type: new Abstract: With the recent surge of generative models, diffusion-based approaches have become mainstream for view synthesis tasks, either in an explicit depth-warp
arXiv:2605.11059v1 Announce Type: cross Abstract: We study the large-depth limit of transformers trained with AdamW, by modelling the hidden-state dynamics as an interacting particle system (IPS) coup
arXiv:2605.11856v1 Announce Type: cross Abstract: Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on
arXiv:2605.11170v1 Announce Type: new Abstract: Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model uti
arXiv:2605.11710v1 Announce Type: cross Abstract: Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it i
arXiv:2605.11258v1 Announce Type: cross Abstract: Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that c
arXiv:2605.11634v1 Announce Type: new Abstract: Although Vision Language Models (VLMs) have seen tremendous progress across all kinds of use cases, they still fall behind in answering questions regard
arXiv:2605.11166v1 Announce Type: new Abstract: Political and social identities structure how people evaluate political information, a finding decades deep in political science and routinely discarded
arXiv:2605.11782v1 Announce Type: new Abstract: Visual impairment affects hundreds of millions of people worldwide, severely limiting their ability to navigate urban environments safely and independen
arXiv:2605.11131v1 Announce Type: new Abstract: Accurate medical image segmentation is an integral part of the medical image analysis pipeline that requires the ability to merge local and global infor
arXiv:2605.11865v1 Announce Type: cross Abstract: Standard Bradley--Terry (BT) reward models are limited when human preferences are pluralistic. Although soft preference labels preserve disagreement i
arXiv:2605.11196v1 Announce Type: new Abstract: Linear attention reduces the quadratic cost of softmax attention to O(T), but its memory state grows as O(T) in Frobenius norm, causing progressive inte
arXiv:2605.11913v1 Announce Type: new Abstract: Differentiable vector graphics have enabled powerful gradient-based optimization of vector primitives directly from raster images. However, existing fra
arXiv:2605.11334v1 Announce Type: cross Abstract: LLM-as-Judge systems are widely deployed for automated evaluation, yet practitioners lack reliable methods to know when a judge's verdict should be tr
arXiv:2605.10974v1 Announce Type: new Abstract: Certified verification of transformer attention requires bounding the softmax function over interval constraints on the pre-softmax scores. Existing ver
arXiv:2605.11864v1 Announce Type: cross Abstract: Listwise reranking is a key yet computationally expensive component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG)
arXiv:2406.05615v4 Announce Type: replace Abstract: Humans use multiple senses to comprehend the environment. Vision and language are two of the most vital senses since they allow us to easily communi
arXiv:2605.11424v1 Announce Type: new Abstract: Gaussian Splatting has achieved remarkable progress in multi-view surface reconstruction, yet it exhibits notable degradation when only few views are av
arXiv:2605.12325v1 Announce Type: new Abstract: Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial
arXiv:2602.04476v2 Announce Type: replace Abstract: Despite recent advancements in Multi-modal Large Language Models (MLLMs) on diverse understanding tasks, these models struggle to solve problems whi
arXiv:2603.11383v2 Announce Type: replace Abstract: Teleoperation of low-cost robotic manipulators remains challenging due to the difficulty of retargeting human hand motion to robot joint commands. W
arXiv:2605.11307v1 Announce Type: new Abstract: Image-to-code generation tests whether a vision-language model (VLM) can recover the structure of an image enough to express it as executable code. Exis
arXiv:2605.11551v1 Announce Type: cross Abstract: Detecting out-of-distribution (OOD) samples is critical for safe deployment of neural networks in safety-critical applications. While maximum softmax
arXiv:2605.11654v1 Announce Type: new Abstract: Cross-view geo-localization (CVGL), which matches an oblique drone view to a geo-referenced satellite tile, has emerged as a key alternative for autonom
arXiv:2502.11981v3 Announce Type: replace Abstract: Decades of research in machine learning have given us powerful tools for making accurate predictions. But when used in social settings and on human
arXiv:2605.11963v1 Announce Type: new Abstract: This paper examines what it means for a medical AI system to be right by grounding the question in a specific clinical context: the automatic classifica
arXiv:2605.12281v1 Announce Type: new Abstract: What makes a word difficult to learn, and how does the difficulty depend on the learner's native language? We computationally model vocabulary difficult