论文库

On-device inference requires kernels that make effective use of local accelerators. Efficient training and evaluation of models that generate Apple Metal kernels benefit from native macOS tools and concurrent agent sessions. These sessions alternate between model requests, development commands, and GPU execution, leaving GPU capacity idle for much of a rollout. We present Metal Sandbox, infrastructure that combines restricted per-instance file access, native command execution, and command-level scheduling across interconnected Macs. Each agent retains its workspace and private development environment. Parallel commands can run concurrently, while serial commands share one execution slot per node; eligible waiting commands can migrate to available Macs and return results to the original agent. Integration with Harbor supports task execution, automatic verification, and rollout collection through a common workflow. Controlled experiments on four Mac mini M4 nodes achieve $1.68\times$--$2.05\times$ gains in command throughput under concentrated demand. Sixteen static agent traces give an estimated $2.14\times$ sustained-throughput gain for four sessions per node versus one, assuming continuously replenished sessions and unchanged mean durations. Replaying these measured traces under dynamic scheduling reduces mean tool waiting by 18.8% and batch elapsed time by 22.3%, assuming unchanged phase durations. Metal Sandbox and its Harbor integration are open-source on GitHub.

Variability is an inherent characteristic of modern GPU systems, arising from a combination of process variation, dynamic environmental conditions, and power management decisions. Prior work has characterized inter-GPU variability and found consistent performance differences across GPUs. However, we observe that modern workloads, particularly large language models (LLMs), exhibit significant intra-GPU variability. Their short-running kernels interact poorly with the coarse granularity of dynamic power management mechanisms, leading to unpredictable performance. A key source of this intra-GPU transient variability is power excursions, also referred to as electrical design power peaks (EDP$_{p}$), where power temporarily exceeds the GPU's rated power limits. While power management mechanisms are designed to ensure reliable operation despite the presence of EDP$_{p}$ sustained power peaks cause throttling that detrimentally impacts overall application performance. To the best of our knowledge, our work is the first to characterize the magnitude and frequency of EDP$_{p}$, showing that frequent, significant power overshoots are especially common in ML workloads, which combine high power draw, short kernels, and rapidly changing compute demands. To address this, we design and leverage hardware and firmware mechanisms to provide consistent power management behavior that reduces intra-GPU variability due to EDP$_{p}$ and improves overall performance. We evaluate our techniques across a range of popular workloads. Our approach improves performance by 3-12% over state-of-the-art GPU power management and comes within 3% of an oracular solution.

Most multimodal sentiment analysis algorithms focus on point-wise regression. While straightforward, it uses absolute values to represent subjective sentiment and overlooks the ordinal nature of sentiment, resulting in unstable predictions and poor correlation. Inspired by the way humans perceive sentiment, pair-wise ordinal learning frameworks emerged to address this gap, capturing relative order by learning from comparisons. However, they have two limitations: First, they assign uniform importance to all pairs, failing to adaptively focus on hard-to-rank samples. Second, they employ static ranking margins, which fail to reflect the varying semantic distances between sentiment groups. To address this, we propose a Group-wise Ranking and Calibration Framework (GRCF) that introduces the Adaptive Error-weighting and Dynamic Margin mechanism, which resolves these limitations by simultaneously preserving the relative ordinal structure and ensuring absolute score calibration. Specifically, Stage 1 introduces a Group-aware Ranking Loss to build a fine-grained ordinal structure by assigning higher optimization priority to confusable pairs. Stage 2 then employs an MAE-driven objective to align the prediction magnitudes. To validate its generalizability, we extend GRCF to classification tasks, including Multimodal Humor and Sarcasm Detection. It achieves state-of-the-art performance on regression datasets while also showing strong generalizability in classification tasks.

Large language models (LLMs) are increasingly being used to support computer science research. To contribute reliably, these systems must be able to work with information distributed across research papers and across different aspects of the research process. However, large-scale resources that systematically organize such information into structured supervision for both model evaluation and post-training remain limited. To address this gap, we propose a systematic paper-to-QA construction pipeline that organizes information from AI research papers into structured QA pairs supported by source evidence. Using this pipeline, we construct CS-54k, a 54k-pair corpus derived from 14,474 openly licensed AI research papers. The corpus covers eight recurring paper components, including research domain, prior work, existing challenges, motivation, findings and assumptions, methods, experimental settings, and experimental results. We further derive two complementary subsets: CS-4k, a benchmark for evaluating LLMs on paper-derived research QA, and CS-50k, a companion corpus for post-training. Extensive evaluations on CS-4k reveal substantial performance differences across existing LLMs and paper components, with experimental settings and results remaining particularly challenging. Moreover, post-training on CS-50k substantially improves Qwen2.5-7B-Instruct on CS-4k, demonstrating the practical utility of structured, paper-derived supervision. Together, CS-4k and CS-50k provide a unified and scalable resource for benchmarking and improving LLMs on research paper question answering.

Provably secure linguistic steganography assumes that the receiver recovers the sender's tokens, but a text channel delivers only text, and ambiguous tokenizations break extraction. Existing fixes change the distribution, synchronize whole pools of tokens at a capacity that collapses with large vocabularies, or track several token histories. We prove that if extraction is exact and error-free across full-support language models, a single-history receiver is confined to a prefix-free candidate set at every step -- even if it reads the entire future text and the sender constrains later steps -- and must therefore give up the stop entropy, the entropy of deciding whether each prefix token ends there. Fixing these stop decisions on the prefix forest with shared randomness yields coin projection: a closed-form scheme that attains the bound, works with any distribution coder in one model call per token, preserves ordinary sampling, and refines SyncPool for every key. Across English, Chinese and Japanese, ambiguous text is rare (at most 11 in 1,000 tokens), yet the stop entropy at word and morpheme prefixes takes 7.2-9.0% of the entropy at every step; SyncPool's further loss comes from space and single-byte UTF-8 hubs that merge subtrees while carrying almost no stop uncertainty. Coin projection keeps 91-93% of the string entropy for the coder at every vocabulary size; with the full vocabulary, it turns 2.16-6.85 times as much entropy into message bits as SyncPool and recovers every completed message.

We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency. An event-driven agent maintains persistent task events and reassesses plans when progress or feasibility changes, enabling cross-task retrieval and conditional task resumption. MR0 achieves 93.6% success on RoboTwin 2.0 and ranks fifth in the RoboDojo VLA track. Under matched HG-DAgger post-training, MR0 achieves higher average success rate and progress score than $π_{0.5}$ across three real-robot tasks. On Ethernet insertion, CFG-DAgger trained with Rollback data reaches 70% success and a progress score of 0.90. Qualitative agent deployments demonstrate cross-task event retrieval and recovery from temporarily unsatisfied task conditions.

We give faster algorithms for diameter and farthest-neighbor search in high-dimensional Euclidean space. For every fixed $1<c<\sqrt2$, we maintain an actual factor-$c$ diameter pair under arbitrary point insertions and deletions, with worst-case update time $n^{2/c^2-1}\poly(d,\log n)$ and space $n^{2/c^2}\poly(d,\log n)$, suppressing logarithmic dependence on the execution length and failure probability. Here $n$ bounds the number of active points. The update exponent improves Indyk's algorithm~\cite{indyk} (SODA'03) bound from $1/c^2$ to $2/c^2-1$, while the space exponent improves from $1+1/c^2$ to $2/c^2$. At $c=\sqrt{3/2}$, the update exponent decreases from $2/3$ to $1/3$. A separate construction achieves approximation exactly $\sqrt2$ with update time polynomial in $d$ and $\log n$. All these guarantees hold against adaptive updates, even when every previous random choice is exposed. We also improve the time--space tradeoff near linear space. This construction has an always-correct variant with expected amortized update bounds and requires no advance bound on the number of updates. The dynamic structures store a current answer, so reporting its two point identifiers takes constant time. The geometric method also gives static diameter algorithms and a farthest-neighbor structure for a fixed set that answers arbitrary adaptive queries. At approximation $\sqrt2-\varepsilon$, the diameter time is $n^{1+O(\varepsilon)}$, and the query time is $n^{O(\varepsilon)+o(1)}$ with near-linear preprocessing and space, up to polynomial input-parameter factors. On binary points, this improves the $n^{O(\sqrtθ)}$ overhead of the algorithm that Andoni, Jiang, and Zharkov~\cite{ajz2026} (STOC'26) for Hamming approximation $2-θ$ to $n^{O(θ)+o(1)}$.