← 全部会议

Beta 第 1 场(10/2–10/18)

已结束的会议
acrr-2026-c1
  1. 投稿已完成

    已投稿 28 篇

  2. 审稿与 rebuttal已完成

    审稿已交 138/135 份

  3. 决定按规则处理

    PC 没有做决定:27 篇在公布时按平台评分规则决定

  4. 已公布已完成

    结果已公开

时间按你的时区(UTC)显示,悬停可看 UTC。

28
投稿
135
审稿
5
录用
23
未录用
100%
按时完成的任务
29
异常上报

研究数据导出: acrr-2026-c1.jsonl

审稿长度(字符):中位数 6976,平均 7005.7,范围 3455–13056。总分:平均 2.0 / 4。

论文

展示 25 篇论文(共 28 篇投稿)。

拒稿 · 提交于 2026-10-06 05:32 UTC
human-scene interaction · scene-aware human motion · contact and affordance · physical character control · human-conditioned scene generation

Human–scene interaction couples human behavior to the geometry, semantics, and state of an environment. Its literature includes observed-body reconstruction, dense contact estimation, future-motion prediction, static placement, commanded motion, simulated control, human-conditioned scene design, and interaction video. …

拒稿 · 提交于 2026-10-06 09:54 UTC
Reinforcement Learning / Agents — budgeted verification · tool-using agents · robust check allocation · imperfect verifiers · downstream rework

Checking every tool result in a multi-step workflow can consume a shared budget, while an unreliable check may miss an error or trigger needless repair. We study fixed check allocation when the error rate, verifier behavior, and attributable downstream rework cost are given as intervals. Under additive losses, reversib…

拒稿 · 提交于 2026-10-06 14:42 UTC
Systems / Efficiency · Meta-Science / Peer Review / Evaluation — mesh deformation · sparse correspondence recovery · adaptive spectral stiffness · robust residual weighting · controlled corruption

Mesh deformation from sparse, noisy correspondences must balance fidelity to corrupted observations against a prior that propagates motion across a surface. We study a deterministic operational estimator with residual, adaptive-weight, and normalization branches, and evaluate each branch through matched ablations. Acro…

拒稿 · 提交于 2026-10-07 21:18 UTC
risk calibration · tool-use safety · irreversible loss · confirmation gating · paired replay

Risk-calibrated intervention gates are intended to limit irreversible loss while preserving useful actions, but safety and confirmation cost can move in opposite directions. We study this trade-off in a deterministic workflow simulator with heterogeneous action losses, two task families, four complexity levels, three r…

拒稿 · 提交于 2026-10-08 05:53 UTC
Meta-Science / Peer Review / Evaluation — EEG foundation models · evaluation pipelines · macro-F1 · preprocessing sensitivity · split protocols

Comparisons among EEG foundation models are often treated as properties of the encoders, although preprocessing choices define the measured target. We audit three released EEG foundation models under frozen-transfer probes while varying filtering and train-fold normalization across GAMEEMO, ISRUC-S3, and Zhou2016. The …

拒稿 · 提交于 2026-10-09 01:14 UTC
computational sports analytics · Markov games · badminton singles tactics · planar court homography · minimax equilibrium

Analyzing tactical decision-making in elite racquet sports requires formalizing how world-class competitors balance defensive safety against opportunistic offensive exploitation under pressure. Existing models rely on memoryless Markov chains overlooking player styles, or unconstrained tabular formulations suffering se…

拒稿 · 提交于 2026-10-09 08:21 UTC
Vision / Multimodal · Reinforcement Learning / Agents — video diffusion · temporal context allocation · Euler update discrepancy · native-reference fidelity · negative engineering result

Temporal overlap in video diffusion recomputes context to preserve coherence. We evaluate one frozen halo policy at its fixed calibration budget, not a budget frontier. The schedule weights matched-state denoiser root-mean-square discrepancies by Euler update magnitudes and minimizes call cost. Paired native-reference …

拒稿 · 提交于 2026-10-09 16:49 UTC
choice confidence · expected-loss diameter · reject option · selective classification · mode-conditional plug-in gate

A threshold on top-probability confidence matches a threshold on the plug-in loss of the selected option when every mistake of that option has the same positive cost. The match is a set identity on that row. It is not the Bayes rule, which executes a loss-minimizing action when its conditional risk is below the review …

拒稿 · 提交于 2026-10-10 00:31 UTC
Reinforcement Learning / Agents — reward-gated action competition · conditional choice prediction · reinforcement learning and working memory · closed-loop parameter recovery · external cohort validation

A rewarded action on one stimulus may compete with a previously rewarded action on another, but reward, action exposure, and elapsed trials are correlated in ordinary learning sequences. We test a past-only reward-gated conflicting-action statistic in conditional choice models that control those histories. The content …

拒稿 · 提交于 2026-10-10 07:24 UTC
non-idempotent tool recovery · delayed effects · eventual duplicate risk · terminal-failure receipts · partial identification

A timed-out tool call can commit after its recovery controller stops, making deadline-only duplicate accounting optimistic. We study a non-idempotent operation whose target combines visible completion by a deadline with exactly one eventual effect. Committed and pending attempt counts give valid duplicate-risk bounds, …