AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory

Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps. While existing research leverages video priors for consistency, their reliance on bidirectional attention is fundamentally misaligned with the causal, sequential nature of interactive editing. In this paper, we propose AnchorEdit, the first autoregressive (AR) diffusion-based framework designed specifically for high-resolution, long-term multi-turn editing. AnchorEdit bridges the gap between video priors and causal inference through a three-stage training curriculum: identity-preserving sing-turn pretraining, causal AR forcing fine-tuning with a novel self-rollout strategy to mitigate exposure bias, and consistency distillation for efficient 4-step generation. During inference, we introduce a memory mechanism to anchor the initial subject identity and ensure stable extrapolation across extended editing trajectories. To evaluate performance, we provide a new high-resolution multi-turn editing benchmark designed to stress-test long-horizon stability. Extensive experiments demonstrate that AnchorEdit achieves state-of-the-art results, maintaining exceptional subject fidelity and instruction following even over 10+ interaction rounds.

Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization

Learning from human video demonstrations remains challenging due to noisy hand-object interactions, unseen objects with partial observation, and cross-embodiment discrepancy. To address these challenges, we present \textit{HOWTransfer} (\emph{H}and-\emph{O}bject \emph{O}pen-\emph{W}orld Transfer), a hand-centric framework that distills human demonstrations into contact-aware, taxonomy-informed, and diverse robotic trajectories. Instead of relying on object-specific descriptions, vision-language queries, or explicit object-state tracking, \emph{HOWTransfer} recovers temporally consistent 3D hand motion and localizes temporal contact intervals by reasoning over observed hand-object interaction cues. The localized contact onsets are then used to retarget human grasp intent into multi-modal parallel-jaw grasp hypotheses, which are propagated along the recovered wrist trajectory to generate robot-executable motions. Finally, a trajectory editing stage refines contact alignment and produces diverse executable variants from a single demonstration. Experiments across diverse manipulation tasks show that \emph{HOWTransfer} enables accurate contact localization and high-quality robot motion retargeting with $86\%$ success, which is preferred over teleoperated trajectories in a blinded preference study.

Autonomous FPV Flight with Translational Optical Flow and Uncertainty Mask

Autonomous FPV quadrotor flight in complex environments using a monocular RGB camera as the sole exteroceptive sensor remains a fundamental challenge. Recent research has shown that using optical flow as the input of a neural network can achieve end-to-end autonomous flight in cluttered scenes. However, extracting the most relevant information from the flow estimation is the key bottleneck limiting agility and robustness. Existing methods struggle to disentangle obstacle-induced optical flow from the ego-motion background flow and suffer from low signal-to-noise ratios near the focus of expansion (FoE). To address these issues, we decompose the optical flow into translational and rotational components and utilize only the translational flow, which captures scene geometry and depth cues. In addition, we introduce an uncertainty mask derived from inconsistencies between forward and backward flow estimates. This mask highlights obstacle structures, including those within the FoE region. Both cues are fed to a control policy trained in a differentiable simulation framework, which enables efficient first-order optimization across perception and control. We validate our approach through extensive experiments in both simulated and real-world forest environments. The proposed system achieves robust flight at speeds of up to 13.91 m/s in simulation and 11.79 m/s in real-world tests, with a 93.3\% success rate over 30 real-world trials, nearly doubling the previously reported 6 m/s real-world speed of the monocular-RGB optical-flow UAV obstacle avoidance system.

ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer

The rapid proliferation of Agent Development Kits (ADKs), SDK-level frameworks for building LLM-powered autonomous agents, has outpaced any empirical understanding of how framework choice affects agent performance. We propose \textbf{LLM-as-a-Developer}, a methodology that replaces human developers with an LLM coding agent that learns each framework's API from documentation, writes agent code, and iteratively repairs it through a validate-and-feedback loop until tests pass. By holding the developer constant and varying only the framework, generation effort becomes a quantitative proxy for API usability and the resulting agents provide a controlled measure of framework effectiveness. We implement this in \textbf{ADK Arena}, a fully automated pipeline with per-framework Docker isolation, a three-level validation pipeline, and benchmark adapters for SWE-bench, $τ^2$-bench, Terminal-Bench, and MCP-Atlas. Evaluating all 51 popular Python ADK frameworks (204 agent--benchmark pairs), we find that: (1)~generation succeeds for 57\% of runs, and its cost varies 5.6$\times$ across frameworks (\$0.6 to \$3.4 per agent), a quantitative proxy for API complexity, though cost alone does not predict success; (2)~no single framework dominates: the best single-benchmark ADK agents resolve up to 80\% of tasks and can even \emph{beat} general-purpose frontier coding agents at a fraction of the cost, yet the median framework resolves only 32\%; (3)~across information-source ablations, genuine framework usage stays within a narrow 28--40\% band (highest with raw source access and still 33\% with no reference material at all), indicating that documentation, source code, and parametric knowledge are largely substitutable rather than any one being a hard bottleneck.

YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Models

Contrastive decoding (CD) seeks to mitigate hallucinations in Large Vision-Language Models (LVLMs) by contrasting the output distributions of a standard model and a visually degraded model. However, existing training-free CD methods suffer from sub-optimal degraded branches: completely dropping visual tokens is too extreme and induces language hallucinations, while corrupting input images offers coarse control over visual evidence and suffers from high inference latency due to requiring two full forward passes. To address these dilemmas, we propose YARD, a training-free Y-Architecture Register Decoding framework. Motivated by the observation that reliable text-to-vision grounding predominantly emerges in the middle decoder layers, YARD constructs the degraded branch internally by sharing shallow-layer computations and branching exactly at this critical stage. For the degraded branch, YARD replaces patch-level visual tokens with register tokens, which preserve global image semantics but lack fine-grained local evidence. This image-aware yet locally under-grounded design provides a faithful contrastive signal without extreme modality mismatch, while the Y-architecture strictly avoids a costly second forward pass. Extensive experiments on generative and discriminative hallucination benchmarks demonstrate that YARD consistently achieves state-of-the-art hallucination mitigation across multiple LVLMs, alongside a significant reduction in inference latency.

Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift

Continual Learning (CL) is a practical paradigm to utilize power of deep pre-trained neural networks, but which pre-trained model has a better ability to balance ``Plasticity-Stability", deserving to be chosen? The logit shift serves as a natural proxy because it represents the logit shift in CL scenarios. However, obtaining the logit shift requires huge computational cost, which hinders large-scale model selection. Existing theoretical analyses fail to offer an efficient alternative because of the assumption of uniform hidden layer widths, which ignores the structural heterogeneity (variable width and depth) of real-world architectures. This raises a critical question: what theoretically relationship can be identified between heterogeneous architecture and logit shift on prior tasks (that the model has been trained on)? To answer the question, we decouple logit shift into architecture dependency and data dependency to establish our framework, which reveals that the combination of two dependency, defined as Architecture-driven Shift (ADS), that can capture the logit shift tendency well computable with few data samples. Specifically, for a well-optimized model on prior tasks, higher ADS is associated with a larger logit shift after training on the current task, which derived based on three mechanistic components: (1) spectral norm scaling of weight matrix gradients with layer width, (2) the optimization path length of the new task, and (3) the asymptotic task conflict in wide networks. Extensive empirical results across more than 175 diverse architectures demonstrate a strong monotonic correlation (the weakest Spearman's $r_s=0.731$) between ADS and logit shift. Practically, we demonstrate that ADS can serve as a lightweight proxy of the expected calibration error, which is a widely used metric for reliable CL model selection, on three datasets across six scenarios.

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation

Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and a chaotic trial-and-error process as equivalent. We show that this equivalence is empirically false. We evaluate 2,614 OpenHands trajectories from eight model backends on 60 SWE-bench Verified tasks. Of these, 47 have enough passing trajectories to construct task-level process references, yielding a 1,815-trajectory evaluation subset. Among passing trajectories in this subset, 10.7% exhibit behavior we call a Lucky Pass: regression cycles, blind retries, missing verification, or temporally disordered exploration, implementation, and verification. We introduce AgentLens, a framework for process-level assessment of SWE-agent trajectories, and release AgentLens-Bench, a dataset of 1,815 trajectories annotated with quality scores, waste signals, divergence points, and 47 task-level Prefix Tree Acceptor (PTA) references. AgentLens builds PTA references by merging multiple passing solutions for the same task, and uses a context-sensitive intent labeler to assign actions to Exploration, Implementation, Verification, or Orchestration based on trajectory history rather than tool identity alone. On AgentLens-Bench, the quality score separates passing trajectories into Lucky, Solid, and Ideal tiers and further decomposes Lucky Passes into five recurring mechanisms. Across the eight model backends, Lucky rates range from 0.5% to 23.2%, and some models move by as many as five rank positions when ranked by quality score instead of pass rate. We release the anonymized project repository, including the AgentLens-Bench dataset and AgentLens SDK, at https://github.com/microsoft/code-agent-state-trajectories/.

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser token-level supervision by training on student-generated trajectories, yet existing methods typically distill each rollout independently and ignore the other attempts sampled for the same prompt. We introduce Multi-Rollout On-Policy Distillation (MOPD), a peer-conditioned distillation framework that uses the student's local rollout group to construct more informative teacher signals. MOPD conditions the teacher on both successful and failed peer rollouts: successes provide positive evidence for valid reasoning patterns, while failures provide structured negative evidence about plausible mistakes to avoid. We study two peer-context constructions: positive peer imitation and contrastive success-failure conditioning. Experiments on competitive programming, mathematical reasoning, scientific question answering, and tool-use benchmarks show that MOPD consistently improves over standard on-policy baselines. Further teacher-signal analysis shows that mixed success-failure contexts better align teacher scores with verifier rewards, indicating that the gains arise from more faithful, instance-adaptive supervision. These results indicate that effective on-policy distillation should exploit the student's multi-rollout trial-and-error behavior rather than treating rollouts as isolated samples.

Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes

Feedforward Gaussian Splatting has recently emerged as an efficient paradigm for 4D reconstruction in autonomous driving. However, in unstructured off-road scenes, its performance degrades due to high-frequency geometry, ego-motion jitter, and increased non-rigid dynamics. These factors introduce conflicting Gaussian observations across timestamps, leading to either over-smoothed renderings or structural artifacts. To address this issue, we propose Ground4D, a spatially-grounded 4D feedforward framework for pose-free off-road reconstruction. The key idea is to resolve temporal conflicts through spatially localized conditioning. Specifically, we introduce voxel-grounded temporal Gaussian aggregation, which partitions the canonical Gaussian space into spatial voxels and performs query-conditioned temporal attention within each voxel. Intra-voxel softmax normalization ensures that temporal selectivity and spatial occupancy become mutually reinforcing rather than conflicting. We furthermore introduce surface normal cues as auxiliary geometric guidance to regularize the geometry of Gaussian primitives. Extensive experiments on ORAD-3D and RELLIS-3D demonstrate that Ground4D consistently outperforms existing feedforward methods in reconstruction quality and generalizes zero-shot to unseen off-road domains. Project page and code:https://github.com/wsnbws/Ground4D.

Learning Correct Behavior from Examples: Validating Sequential Execution in Autonomous Agents

As autonomous agents become increasingly sophisticated, validating their sequential behavior presents a significant challenge. Traditional testing approaches require manual specification, exact sequence matching, or thousands of training examples. We present a novel algorithm that automatically learns correct behavior from just 2-10 passing execution traces and validates new executions against this learned model. Our approach combines dominator analysis from compiler theory with multimodal large language model-powered semantic understanding to identify essential states and handle non-deterministic behavior. The system constructs a generalized ground truth model using Prefix Tree Acceptors, merges traces through multi-tiered equivalence detection, and validates new executions via topological subsequence matching. In controlled experiments, our system achieved high accuracy in detecting product bugs and false successes using only 3 training traces. This approach provides explainable validation results with coverage metrics and works across diverse domains including UI testing, code generation, and robotic processes.