arXiv:2605.10664v2 Announce Type: replace-cross Abstract: Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key failure mode: steered token states are stored and repeatedly reused, turning a local perturbation into cumulative coherence degradation. To […]
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
arXiv:2605.14712v1 Announce Type: cross Abstract: Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample […]
XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference
arXiv:2605.14844v1 Announce Type: cross Abstract: We introduce XFP, a dynamic weight quantizer for LLM inference that inverts the conventional workflow: the operator specifies reconstruction quality floors on per-channel cosine similarity (one strict floor for attention and shared experts, one lazy floor for routed-expert MoE); XFP determines codebook size, outlier budget, and packing per layer automatically […]
Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition
arXiv:2605.14982v1 Announce Type: cross Abstract: We address the discounted reward setting in reinforcement learning (RL). To mitigate the value approximation challenges in policy gradient methods, actor-critic approaches have been developed and are known to converge to stationary points under suitable assumptions. However, these methods rely on first-order updates. In contrast, second-order optimization provides principled curvature-aware […]
On the Cultural Anachronism and Temporal Reasoning in Vision Language Models
arXiv:2605.15071v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital archives to educational platforms. This work identifies a fundamental issue in how these models interpret historical artifacts. We define this phenomenon as cultural anachronism, the tendency to misinterpret historical objects using temporally inappropriate concepts, materials, or cultural frameworks. […]
Quantitative Video World Model Evaluation for Geometric-Consistency
arXiv:2605.15185v1 Announce Type: cross Abstract: Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation pipelines rely heavily on human judgment or learned graders, which can be subjective and weakly diagnostic for geometric failures. We introduce PDI-Bench (Perspective […]
FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
arXiv:2602.01664v4 Announce Type: replace Abstract: In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-dependent workflow construction, the lack of graph-level execution feedback, and the inability to repair errors in-loop during long-horizon construction. To address these challenges, we propose FlowSteer, a […]
Personalized Digital Health Modeling with Adaptive Support Users
arXiv:2605.02004v2 Announce Type: replace Abstract: Personalized models are essential in digital health because individuals exhibit substantial physiological and behavioral heterogeneity. Yet personalization is limited by scarce and noisy user-specific data. Most existing methods rely on population pretraining or data from similar users only, which can lead to biased transfer and weak generalization. We propose a […]
The Impact of Generative AI on Collaborative Open-Source Software Development: Evidence from GitHub Copilot
arXiv:2410.02091v3 Announce Type: replace-cross Abstract: Generative artificial intelligence (AI) facilitates content production and enhances ideation capabilities, which can significantly influence developer productivity and participation in software development. To explore its impact on collaborative open-source software (OSS) development, we investigate the role of GitHub Copilot, a generative AI pair programmer, in OSS development where multiple distributed […]
AVEX: What Matters for Animal Vocalization Encoding
arXiv:2508.11845v3 Announce Type: replace-cross Abstract: Bioacoustics, the study of sounds produced by living organisms, plays a vital role in conservation, biodiversity monitoring, and behavioral studies. Many tasks in this field, such as species, individual, and behavior classification and detection, are well-suited to machine learning. However, they often suffer from limited annotated data, highlighting the need […]
AI-Driven Optimization under Uncertainty for Mineral Processing Operations
arXiv:2512.01977v2 Announce Type: replace-cross Abstract: The global capacity for mineral processing must expand rapidly to meet the demand for critical minerals, which are essential for building the clean energy technologies necessary to mitigate climate change. However, the efficiency of mineral processing is severely limited by uncertainty, which arises from both the variability of feedstock and […]
Finding Interpretable Prompt-Specific Circuits in Language Models
arXiv:2602.13483v2 Announce Type: replace-cross Abstract: Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To this end, we introduce ACC++, an improved circuit-tracing method based on the principle of attention-causal […]