arXiv:2605.13038v1 Announce Type: cross Abstract: Geometric estimation including depth estimation and scene reconstruction is a crucial technique for colonoscopy which can provide surgeons with 3D spatial perception and navigation. However, geometric ground truth in colonoscopy is difficult to obtain due to narrow and enclosed space of the colon, while there is a large feature gap […]
Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models
arXiv:2506.19037v4 Announce Type: replace-cross Abstract: Masked diffusion language models (MDLMs) promise fast, non-autoregressive text generation, yet existing samplers, which pick tokens to unmask based on model confidence, ignore interactions when unmasking multiple positions in parallel and effectively reduce to slow, autoregressive behavior. We propose the Dilated Unmasking Scheduler (DUS), an inference-only, planner-model-free method that partitions […]
Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning
arXiv:2605.13054v1 Announce Type: cross Abstract: Cross-domain offline reinforcement learning aims to adapt a policy from a source domain to a target domain using only pre-collected datasets, where environment dynamics may differ. A key challenge is to leverage source data while reducing distributional mismatch, particularly when the target dataset is extremely limited. To address this, we […]
Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education
arXiv:2605.12988v1 Announce Type: new Abstract: Students learning algorithms often need support as they interpret traces, debug reasoning errors, and apply procedures across unfamiliar problem instances. In this paper, we present KITE (Knowledge-Informed Tutoring Engine), a Retrieval-Augmented Generation (RAG)-based intelligent tutoring system designed to serve as a classroom teaching assistant for algorithmic reasoning and problem-solving tasks. […]
Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems
arXiv:2605.13077v1 Announce Type: cross Abstract: Responsibility allocation — determining the extent to which agents are accountable for outcomes — is a fundamental challenge in the design and analysis of multi-agent systems. In this work, we model such systems as concurrent stochastic multi-player games and introduce a notion of retrospective (backward) counterfactual responsibility, which quantifies an […]
Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation
arXiv:2510.14244v2 Announce Type: replace-cross Abstract: Domain adaptation methods aim to bridge the gap between datasets by enabling knowledge transfer across domains, reducing the need for additional expert annotations. However, many approaches struggle with reliability in the target domain, an issue particularly critical in medical image segmentation, where accuracy and anatomical validity are essential. This challenge […]
SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting
arXiv:2605.12992v1 Announce Type: new Abstract: Neural population models, which predict the joint firing of many simultaneously recorded neurons forward in time, are typically evaluated by a single aggregate Pearson correlation $r$ between predicted and actual spike counts, a number that masks critical structure. We argue that how we evaluate spike forecasting matters as much as […]
SECOND-Grasp: Semantic Contact-guided Dexterous Grasping
arXiv:2605.13117v1 Announce Type: cross Abstract: Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guidance, yet these objectives are often treated as separate, disjoint goals. In this paper, we investigate how to integrate dexterous grasping techniques, i.e., physically stable grasps for object lifting and language-guided grasp […]
Deep Delta Learning
arXiv:2601.00417v3 Announce Type: replace-cross Abstract: Transformer residual streams evolve by additive accumulation: each layer appends a feature update to a shared hidden state, but has no direct mechanism for replacing content that has become obsolete or conflicting. We introduce Deep Delta Learning (DDL), a residual update rule that preserves the identity path while giving every […]
AcquisitionSynthesis: Targeted Data Generation using Acquisition Functions
arXiv:2605.13149v1 Announce Type: cross Abstract: Data quality remains a critical bottleneck in developing capable, competitive models. Researchers have explored many ways to generate top quality samples. Some works rely on rejection sampling: generating lots of synthetic samples and filtering out low-quality samples. Other works rely on larger or closed-source models to extract model weaknesses, necessary […]
Implicit Behavioral Decoding from Next-Step Spike Forecasts at Population Scale
arXiv:2605.12999v1 Announce Type: new Abstract: Closed-loop brain-computer interfaces often require both a forecast of upcoming neural population activity and a readout of the animal’s behavioral state. A single Mamba forecaster, trained only on next-step spike counts at Neuropixels scale, can deliver both in one forward pass. A lightweight per-session linear head reading the model’s predicted […]
Test-Time Training with KV Binding Is Secretly Linear Attention
arXiv:2602.21204v4 Announce Type: replace-cross Abstract: Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping at test time. However, our analysis reveals multiple phenomena that contradict this memorization-based interpretation. Motivated by these findings, we revisit the formulation of TTT and show […]