AffordSim is introduced, a scalable data generator and benchmark that integrates open-vocabulary 3D affordance prediction into simulation-based trajectory generation and achieves 93% of the trajectory collection success rate of manual contact annotations on affordance-critical tasks and 89% on hard composite tasks.
Ming-Yang Li, Hao Xu, Hao-Wen Sun et al.· arXiv.org· 0 citations
The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, automotive and robotic computing platforms, and high-performance embedded systems, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads efficiently, the autoregr...
Jinane Bazzi, Mariam Rakka, Fadi Kurdahi et al.· 0 citations
Generating realistic visual defects is crucial for alleviating the scarcity of abnormal samples in anomaly detection, yet existing methods often rely on category-specific few-shot adaptation and struggle to generalize across objects, defect types, and domains. This limitation stems in part from the lack of paired defec...
Yuanting Fan, Jun Liu, Bin-Bin Gao et al.· 0 citations
Neural routing solvers rarely stop at their first solution: constructed tours are usually refined by search, such as sampling or local search. Neural improvement methods learn this search as a policy that repeatedly applies local moves, but existing policies degrade sharply beyond their training size. We argue that siz...
Andoni Irazusta Garmendia· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This research shows that incentives can moderate AI's homogenizing force in two creative writing tasks where participants can use AI interactively, and releases a rich, anonymized dataset capturing fine-grained trajectories of human-AI co-creation across both studies.
Nathanael Jo, Manish Raghavan· arXiv.org· 3 citations
Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid intermediate reasoning. We propose SAFE, an LLM-as-verifier framework for evidence-grounded multi-hop QA. Rather than judging only the final answer after generation, SAFE verifi...
Genotype Bidirectional Encoder Representations from Transformers model (GenoBERT), a transformer-based, reference-free framework that tokenizes phased genotypes and uses self-attention mechanism to capture both short- and long-range linkage disequilibrium (LD) dependencies, is presented.
Lei Huang, Chuan Qiu, Kuan-Jui Su et al.· arXiv.org· 1 citation
Turbo4DGen introduces a spatiotemporal cache mechanism that persistently reuses intermediate attention across denoising steps, combined with dynamically semantic-aware attention pruning and an adaptive SCM chain bypass scheduler, to drastically reduce redundant SCM attention computation.
This work presents a metric-level study of LLM-mediated search policy learning, studying how LLMs construct and adapt exploration-exploitation strategies under multiple operational definitions of exploration, including informativeness, diversity, and representativeness.
Andrea Carbonati, Mohammadsina Almasi, H. Anahideh· arXiv.org· 1 citation
Generating and preserving metrologically useful quantum states is a central challenge in quantum-enhanced metrology. In low-field atomic magnetometry with multilevel atoms, the nonlinear Zeeman (NLZ) effect is both a resource and a limitation. It can generate internal spin squeezing within a single atomic qudit, but un...
C. Z. Cao, J. Z. Han, M. Xiong et al.· 0 citations
Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling rich interactions across text, images, and videos. Unlike text-only workloads, multimodal requests are inherently heterogeneous, differing by orders of magnitude in latency and memory footprint. Existing LLM serving sys...
It is shown that the transition from productive to redundant reasoning is decodable from late-layer hidden states and representations separate the two phases around first-correct-solution boundaries beyond what position and lexical controls explain, and distinguish correct from incorrect solution endings.
