arXiv:2605.05561v1 Announce Type: new Abstract: Post-training quantization makes large reasoning models practical under tight memory and latency budgets, but it can distort the online signals that drive adaptive test-time compute allocation. Under a fixed cap on the number of newly…
arXiv:2605.06508v1 Announce Type: cross Abstract: Research artifacts are widely shared to support reproducibility, and artifact evaluation (AE) has become common at many leading conferences. However, AE mainly checks whether artifacts work as claimed and can be reproduced. It largely overlooks…
arXiv:2603.05421v3 Announce Type: replace-cross Abstract: Compressing vision-language models for on-device deployment is increasingly important in clinical settings, but knowledge distillation (KD) degrades sharply when the teacher-student capacity gap spans an order of magnitude or more. We argue that, under such…
arXiv:2506.13727v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic interpretability addresses this challenge by…
arXiv:2601.21351v2 Announce Type: replace-cross Abstract: Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensive FFN computation, connected by per-step communication. While AFD enables independent scaling of memory and compute resources,…
arXiv:2605.06664v1 Announce Type: cross Abstract: GUI grounding is a critical capability for enabling GUI agents to execute tasks such as clicking and dragging. However, in complex scenarios like the ScreenSpot-Pro benchmark, existing models often suffer from suboptimal performance. Utilizing the…
arXiv:2604.11535v2 Announce Type: replace Abstract: Solving an NP-hard optimization problem often requires reformulating it for a specific solver — quantum hardware, a commercial optimizer, or a domain heuristic. A tool for polynomial-time reductions between hard problems would let practitioners route…
arXiv:2605.06228v1 Announce Type: cross Abstract: Deterministic policy gradient (DPG) is widely utilized for continuous control; however, it inherently relies on the differentiability of the critic with respect to the action during policy updates. This assumption is violated in practical control…
arXiv:2605.06435v1 Announce Type: cross Abstract: The use of content features, particularly textual and linguistic for fake news detection is under-researched, despite empirical evidence showing the features could contribute to differentiating real and fake news. To this end, this study investigates…
arXiv:2605.05409v1 Announce Type: new Abstract: Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence–structured tables, textual narratives, and footnotes–scattered across corporate filings. Existing retrieval-augmented generation (RAG) approaches adopt a single-pass retrieve-then-generate paradigm that struggles with the…
