We prove that exact decision-$\mathsf{SVP}$ in the coefficient $\ell_\infty$-norm is $\mathsf{NP}$-complete for principal ideals and free modules of rank two over the cyclotomic rings $R_n=\mathbb{Z}[X]/(X^n+1)$, where $n$ ranges over powers of two. For each case, we give a deterministic polynomial-time many-one reduction from the Subset Sum problem. For an instance with $s$ positive input integers, the output lattice has dimension $O(s)$. A solution to the original Subset Sum instance can be recovered in polynomial time from any nonzero output lattice vector of norm at most the specified bound. We also transfer these reductions from $R_n$ to the power-of-two cyclic rings $S_{2n}=\mathbb{Z}[X]/(X^{2n}-1)$. This gives $\mathsf{NP}$-completeness of decision-$\mathsf{SVP}$ in the coefficient $\ell_\infty$-norm for principal ideals and free modules of any fixed positive rank over these rings.
Users often complain that AI assistants such as ChatGPT are getting worse. Some versions do change, but human evaluation leaves a second possibility untested: the people judging may change. We separate the two on Chatbot Arena, a public platform where people compare answers from two anonymous large language models (LLMs) and pick the better one or say both are bad. We study 1,260,967 blind votes cast from May 2023 to August 2024 on pairs of models whose versions are fixed: dated vendor snapshots and models with fixed open weights. For the same pair of unchanged models, the share of votes saying "both are bad" rises by 1.71 percentage points a month on a mean of 17.1%, and by 1.91 points a month in 2024. In fourteen pairs observed often in both 2023 and 2024, it rose in every one, from 15.5% to 23.3%. The ranking does not trend: in 2024, the stronger model's share of decisive votes is flat. The rise holds within the same voter and on the same pair, and across arrival cohorts from their first recorded vote. It holds with prompt controls, in every major language, for dated vendor snapshots, open-weight models and models with stable answer length, and between interface changes. The drift is shared across models: month effects estimated from other models' pairs remove it from each model's own pairs. Platform-wide, the average model would be expected to score 78% against the 2023 average, yet the share of "both are bad" votes ended near where it began. The pattern fits a standard that follows the category's progress, so a product that stands still is judged as declining. Absolute verdicts on AI drifted while relative comparisons held steady, an evaluation drift that matters for LLM leaderboards and for the human feedback used to train models.
Stochastic diffusion samplers often require substantially more neural function evaluations (NFEs) than deterministic samplers to achieve comparable sample quality. Although higher-order discretization accelerates deterministic sampling, its benefits for stochastic sampling remains unclear. We establish matching upper and worst-case lower bounds showing that stochastic samplers with higher-order approximations remain first-order convergent, even with exact score functions. Thus, increasing the approximation order does not generally improve the convergence order. Motivated by this limitation, we introduce forward-value discretization, a training-free framework that evaluates the data/noise prediction model at a lookahead estimate constructed from previous predictions. For deterministic sampling, the resulting Forward DPMSolver (F-DPMSolver), improves sample quality at low NFE budgets through its DDIM-based variant, despite remaining first-order convergent. For stochastic sampling, we develop Forward DDPM (F-DDPM), which evaluates the model at a cleaner lookahead point adjusted for subsequent noise injection. This estimate reuses both the previous model prediction and the previously injected noise. Both variants admit first-order convergence guarantees with one model evaluation per iteration. Across CIFAR-10, ImageNet, FFHQ, and LSUN, F-DDPM consistently achieves lower FID than the evaluated stochastic baselines at matched NFE budgets. With 1.5 times as many NFEs as deterministic baselines, it achieves competitive sample quality, narrowing the practical efficiency gap between stochastic and deterministic sampling. Code is available at https://github.com/Na-Li66/F-DDPM.
RNA sequencing produces rich and diverse datasets of gene expression, offering compelling insights into cellular state and function that have many applications in drug discovery. Modeling such data is challenging due to inherent technical noise and experimental batch effects, as evidenced by many existing transcriptomic foundation models (FMs) underperforming relative to linear baselines. Such results raise the question of whether deep representation learning provides a distinct advantage over the direct use of raw transcript counts. Our work explores this by developing a new self-supervised model, TxFM, with a focus on inductive representation learning evaluations. TxFM employs a masked autoencoding approach tailored to diverse RNA-seq count data, and our ablation study empirically identifies crucial architecture configurations required for strong transfer performance. Additionally, we curate a public training corpus, DiverseRNA-1.4M, and find that TxFM trained on this curated dataset yields high-fidelity gene representations that outperform FMs trained on atlas-scale corpora over 100x larger. Overall, our results indicate that inductive self-supervised learning is a viable modeling approach for transcriptomics representation, provided a careful synthesis of model architecture and training data curation.
作者给出对每个 k≥3 的树宽为 k 的平面图的第一个归纳刻画,并由此推出树宽至多 4 的平面图顶点荫度至多 2。
math.CO · cs.DM
查看原文摘要
We give the first inductive characterization of planar graphs of treewidth $k$ for each $k \geq 3$. Our definition generalizes the well-known inductive definition of planar $3$-trees and the recent definition of so-called planar quasi-$4$-trees [Förster, 2024]. As a key step, which may be of independent interest, we show that every planar triangulation $G$ of treewidth $k$ admits a tree decomposition of width $k$ where each adhesion set induces a cycle in $G$. As an application of planar quasi-$4$-trees, we show that planar graphs of treewidth at most $4$ have vertex arboricity at most $2$. That is, the vertex-set of every planar graph of treewidth at most $4$ can be partitioned into two sets that each induce a forest.
Multiset Deletion Codes: Cyclic Syndrome Constructions, Bounds, and Exact Results
Avraham Kreindel, Isaac Barouch Essayag, Aryeh Lev Zabokritskiy
AI 速读 基于摘要
该论文研究可纠正至多 t 次删除的多重集码,给出基于几何和标签与基数构造的校验子类大小尖锐估计及若干精确结果。
cs.IT
查看原文摘要
We determine sharp class-size estimates for multiset codes over $q$ symbols that correct up to $t$ deletions. For fixed $q,t\ge2$, we prove that the syndrome classes defined by Nathanson's geometric-sum labels modulo $M=1+t+\cdots+t^{q-1}$ differ from their average size by $O(n^{q/p-1})$, where $n$ is the blocklength and $p$ is the least prime divisor of $q$. This exponent is sharp, and every prescribed class has size asymptotic to the average. For prime $q$, all classes have equal size when $n\equiv-1,\ldots,-(q-1)\pmod M$. We also present our radix construction, whose labels are zero and the first $q-1$ powers of $t+1$, starting at $1$, modulo $t(t+1)^{q-2}+1$. We determine its sharp class-size deviation exponent. For even $q\ge4$, its syndrome classes have a smaller deviation exponent, although their average size is smaller. Over four symbols and every $t\ge2$, we show that the radix labels still correct up to $t$ deletions modulo a reduced modulus, which gives bounded deviations and eventually larger classes than either unmodified construction. For a fixed number $k\ge2$ of surviving symbols, we prove that some maximum code contains all constant words, reducing the remaining optimization to multisets with multiplicities below $k$. Finally, for one deletion at length four over $q\ge4$ symbols, we show that the best bound from fractional weights on deletion outputs, rounded down, equals the maximum code size exactly when $q\equiv2,4\pmod6$.
LLM agents increasingly operate in long-horizon, verifier-rich environments, but current self-improvement mechanisms often write episode-derived lessons directly into memory, making local success an unreliable signal for reusable and safe knowledge. This paper addresses the core question of when an experience-derived behavioral update should be admitted into persistent agent state. We propose Falsification-Gated Self-Evolution (FGSE), a verifier-grounded framework that represents each candidate lesson as a structured hypothesis with an explicit precondition, behavior change, expected effect, and verifier. FGSE applies the hypothesis only in a temporary state, tests it on target-transfer, falsification, and archived-regression probes, and then commits, refines, or rejects it according to measured gain and risk. Across web, app, tool-use, and long-term memory benchmarks, FGSE achieves strong task performance, including 39.8 WebArena success rate, 78.8 AppWorld average completion, and 0.724/0.487 Pass$^1$ on $τ$-Retail/$τ$-Airline, while reducing falsification failures to 5.0%, regression damage to 1.3%, and harmful committed updates to 3.6%. These results suggest that testing memory updates as hypotheses supports more reliable long-term adaptation.
Unsupervised video object-centric learning aims to decompose dynamic scenes into persistent, object-level representations without supervision. However, existing slot-based methods struggle to maintain stable object identity in challenging settings such as rapid motion and partial occlusion. First, they typically encode both the per-frame appearance of an object and its identity across frames in a single slot vector, creating an objective conflict that leads to slot swapping: reconstruction requires sensitivity to transient visual changes, whereas temporal consistency requires invariance to them. Second, the token renormalization used in Slot Attention can amplify weakly attending slots, allowing them to absorb tokens from other objects and destabilize slot-to-object correspondence. We propose Dual-State Slot Attention (DSSA), a fully self-supervised framework that addresses these limitations by separating appearance from identity and by reducing spurious updates from weakly matching slots. DSSA decomposes each slot into a local state for per-frame appearance and an identity state for temporally stable object information, thereby aligning reconstruction and temporal consistency with separate representations. The identity state is updated through a learned recurrent transition that acts as a temporal filter on the local state, while competition-modulated aggregation (CMA) down-weights updates from weakly matching slots and prevents them from absorbing tokens from other objects. Experiments on MOVi-C, MOVi-D, and YouTube-VIS demonstrate that DSSA consistently improves segmentation quality and temporal consistency over prior methods, while also yielding stronger downstream object recognition and video dynamics prediction. Code is available at https://uark-aicv.github.io/dssa/.
Text encoders turn earnings calls into vectors for search, for language models that answer from retrieved passages, and for forecasting models. A live retriever can use an encoder trained once on all available text, as finance retrievers are, but a backtest needs an encoder that read no text written after the date of each vector. To address this look-ahead bias, from 412,248 calls we train vintages under four pretraining recipes, with yearly cutoffs from 2010 to 2024, and each vintage reads only text dated on or before its cutoff. We then fine-tune each vintage on the question-answer pairs of the calls themselves. The vintages we train on calls alone, with 33.8M parameters, retrieve answers on held-out calls better than the general retrievers we tested in every test quarter. Their vectors also raise by about half the rank correlation between next-day returns and forecasts built from past returns and firm size. When each vintage continues the previous one, a later vintage retrieves better on earlier quarters than the vintage available at the time, and a point-in-time language model that answers from the passages the later vintage retrieves inherits the gain. The 2024 vintage of our families also forecasts earnings surprises better, although the interval of this gain includes zero on calls that no vintage read. It forecasts returns no better, so point-in-time vintages matter most for retrieval and little for forecasts of returns.
Language-model systems use self-judgment to decide which answers to release, review, or recompute. Because intervention is costly, an assurance score must rank errors well at the available budget, not merely over the full ranking. We compare the judge's continuous verdict-token score with a supervised correctness probe trained on attention-head activations from the same prompt. Exact identities link fixed-budget error recall to residual risk and show that AUROC averages recall over all budgets. Across three open 7-12B models on GSM8K and MATH, the probe finds 1.3-22.5 additional percentage points of errors at 5% review in all six model-dataset settings (median 7.4 points). At 10% routing, probe-guided allocation improves accuracy over equal-cost random allocation in both GSM8K experiments, but beats judge-guided routing only for the weaker judge. Cross-dataset transfer lowers probe AUROC for every model in both directions relative to target-domain training. Because dataset, weight precision, and generation budget change together, this measures a joint protocol shift rather than a dataset-only effect. Internal signals can improve supervised, in-domain budget allocation, but are not domain-general confidence estimators.
Kostka numbers, the coefficients of Schur polynomials, count semistandard Young tableaux of prescribed shape and weight. We give a deterministic algorithm for approximating Kostka numbers within a simply exponential factor in the number of variables and the size of the partition. Our approach combines Gurvits capacity bounds for log-concave polynomials with an algorithm for approximating the Gurvits capacity of a Schur polynomial. For a Schur polynomial in $n$ variables indexed by $λ$, we show that the logarithm of the capacity associated with any nonzero coefficient can be approximated to additive error $ε$ in time polynomial in $n$, $|λ|$, and $\log(1/ε)$. The analysis establishes an explicit bounded optimization region and efficient approximate first-order oracles, and handles boundary weights through a factorization into smaller Schur polynomials.
External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it follows a lesson that is incorrect, or misapplies or misreads a valid one. This is because lessons are inferred from trajectories labeled only with task success or failure, yet are typically provided without the trajectories they came from, leaving the agent no way to check them. To address this, we introduce WikiTrace, an evidence-linked memory system designed to let agents check each lesson against its original trajectory. Specifically, motivated by the finding that a trajectory often still holds the evidence needed to catch an erroneous lesson, WikiTrace stores each lesson as a concise insight linked to a summary of why its trajectory succeeded or failed and to the raw trajectory itself. Then, on a new task, the agent starts from all insights and, whenever one lacks details needed to act, conflicts with another, or comes from a failed task, descends through its links with terminal tools to fill in missing details or correct the insight before acting. We validate WikiTrace on five agentic benchmarks, showing that it consistently outperforms existing memory approaches and a baseline given the same insights alone, while also reducing memory-induced degradation. Our code is available at https://github.com/yukyeongleee/wikitrace
This paper determines the accepting-state spectrum of the right-quotient operation for permutation automata, solving an open problem posed by Rauch and Holzer. They showed that in the unary case in which the languages whose right quotient we consider are languages over an alphabet with but one symbol, the accepting state complexities which could ensue for automata recognizing their quotient is exactly all integers between $1$ and $mn$ inclusive when $m,n \ge 1$; we show that for arbitrary alphabets the accepting-state spectrum is $g^{\operatorname{asc}}_{-1,\mathrm{PFA}}(m,n)=\{0\}$ if $m=0$ or $n=0$, and $g^{\operatorname{asc}}_{-1,\mathrm{PFA}}(m,n)=\mathbb{N}_{>0}$ if $m,n\ge 1$. Our result shows that every positive accepting-state complexity ensues for right quotient as long as both of the languages of which we consider the right quotient are nonempty. $0$ becomes the only unavoidable magic value. Moreover, we show that an alphabet with just two letters can witness any arbitrary $α\ge 1$ when $m,n \ge 1$, in that languages can be defined over a binary alphabet with accepting-state complexity $m$ and $n$ respectively for which their right quotient has accepting-state complexity $α$. What ultimately happens in our proof is that we construct $(A^{\mathrm q}_{m,α},B^{\mathrm q}_{n,α})$ such that the words accepted by $B^{\mathrm q}_{n,α}$ induce a point stabilizer in a symmetric group, and the standard quotient construction giving an automaton recognizing the quotient language then saturates the original final set of $A^{\mathrm q}_{m,α}$ to a full orbit; this gives a minimal quotient automaton with exactly $α$ final states. The complete spectrum which is our result follows from this, solving the open question of what the right quotient's accepting-state complexity for permutation automata is.
MammothDP: Private Boosted Decision Trees Ready for Trusted Hardware and Leakage-free Hyperparameters
Moritz Kirschte, Thorsten Peinemann, Kari Kostiainen, Jan Wichelmann, Thomas Eisenbarth, Esfandiar Mohammadi
AI 速读 基于摘要
作者提出 MammothDP,将 S-BDT 梯度提升决策树与隐私过滤器、时序侧信道加固和 TEE 部署结合,并引入无隐私开销的早停准则与改进的回滚保护。
cs.CR · cs.DB · cs.LG
查看原文摘要
Data spaces like the European Health Data Space (EHDS) require the protection of sensitive data in studies during the data's processing and the study's release alike. In this work, we investigate how to implement this mandate using established trusted execution environments (TEEs) and timing side-channel hardening to protect the processing even under a compromised server, and the state-of-the-art differential privacy (DP) notion to protect the release of studies on tabular data. This combined setup could seem to complete the picture, but in fact raises unexpected security challenges that we mitigate by introducing MammothDP: a significant milestone towards a holistic machine learning system based on the recent gradient boosted decision tree learner S-BDT that is provably DP if used within a privacy filter, timing side-channel hardened, and deployed on a TEE. To achieve a strong privacy-utility tradeoff, we introduce two novel components: an early stopping criterion that adaptively selects the number of trees without any privacy overhead, and an improved rollback protection that is no longer vulnerable under timing side-channel attacks.
Concept vectors aim to enhance model interpretability by linking learned internal representations with human-understandable semantics, but their practical utility is often limited by noisy and inconsistent activations. In this work, we discover the SuperActivator Mechanism: a transformer dynamic that amplifies concept activation gaps, concentrating the most reliable concept evidence into a small set of highly activated tokens, which we call SuperActivators. We theoretically characterize this mechanism, proving that concept-aligned attention produces two competing effects: a tail amplification effect, where gaps among already-high activations grow disproportionately fast, and an equalization effect that eventually dominates as attention concentrates on extreme tokens. We validate the predicted tail amplification empirically, finding that in-concept activation distributions develop well-separated upper tails consistently across models, image and text modalities, and concept types. Moreover, we demonstrate the practical implications of SuperActivators for concept detection and localization. First, using only high-activation tokens as concept indicators improves detection by up to 14 F1 points over competing baselines. Second, restricting detection to the extreme activation tail is not merely sufficient but essential: including activations beyond the top 5-10% of the in-concept distribution introduces noise that degrades performance. Finally, using SuperActivators as instance-specific attribution targets yields more accurate and faithful concept localization heatmaps than using global concept vectors.
The Query Complexity of Envy-Free Division: Cake, Chores, and Mixed Resources
Alireza Farhadi, Mohammadtaghi Hajiaghayi
AI 速读 基于摘要
研究蛋糕、杂务及正负混合资源在无嫉妒分配下的查询复杂度,给出上界协议与下界不可能性结果。
cs.GT
查看原文摘要
We study the query complexity of envy-free division for cake, chores, and resources with both positive and negative values. For arbitrary nonnegative nonatomic chore costs, we give a deterministic exact protocol using $2^{n\log_2 n+O(n)}$ queries and cuts. For both cake and chores, a Las Vegas protocol uses $O(n^{12}\log(2n))$ expected queries and $O(n^{11}\log(2n))$ expected cuts. Conversely, every exact protocol with fixed positive success probability requires $Ω(n^2)$ expected queries in general, even with arbitrarily many output cuts at no query cost. For mixed cake and chores, no uniform finite expected-query bound exists even when every Cut returns the leftmost root or every Cut returns the rightmost root. This holds for any fixed positive multiplicative approximation factor and success probability, already when all net totals are one. An additive impossibility holds on the same normalized domain.
The escalating complexity of deep neural networks hinders the deployment of federated learning (FL) on resource-constrained devices, especially for multimedia applications such as on-device image classification and speech recognition. Parallel split learning (PSL) has emerged as a promising solution by offloading a substantial portion of the computational workload to the server through layer-wise model partitioning, making it particularly suitable for resource-limited visual and speech intelligence scenarios. However, the absence of client-side aggregation renders PSL sus ceptible to severe training divergence and potential convergence failure under heterogeneous data distributions. To address this challenge, we propose PSL-RGHA, a gradient-aligned PSL framework that employs reference gradient half-space alignment mechanism to mitigate training divergence among client devices. PSL-RGHA comprises two novel components: reference gradient progressive construction (RGPC) and gradient half-space alignment (GHA). Specifically, RGPC evaluates the directional consistency of client gradients and progressively synthesizes a robust reference gradient via Weiszfeld updates, effectively approximating the global descent direction. Then, GHA constrains client gradients within the reference half-space defined by RGPC to mitigate gradient conflicts and rectify local updates. Extensive experiments demonstrate that our PSL-RGHA framework outperforms existing baselines in various settings.
Adding abstention to a task-adapted multimodal model can discard correct answers, including capabilities acquired during adaptation. We formulate abstention repair as maximizing correct abstention on unanswerable questions under a budget on newly lost correct answers. We propose ReFrain (Regression-Free Abstention), which combines a linear probe on first-token logits, threshold calibration on held-out image clusters, and a deterministic veto that replaces rejected outputs with the displayed "none of the above" option while preserving all other responses. "Regression-free" denotes zero loss on the calibration set at the zero-budget target. All abstention methods in our main comparison start from the same answering-SFT checkpoint; we separately track lost correct answers, repaired errors, and retained SFT gains. On Qwen2.5-VL-3B, ReFrain at zero budget retains all 57 SFT-gained answers with no losses and improves correct abstention by 7.30 percentage points. At a 0.5% calibration budget, it reaches 74.05% correct abstention with 8 losses and retains 55 gains; CLIP-UP EmbLoRA reaches 64.65% with 62 losses, 41 repairs, and 40 retained gains. The same probe at its default threshold loses 298 correct answers. With models and thresholds frozen, confirmation on 228 independent question clusters yields 66.05% correct abstention and no losses at the 0.5% point, exceeding EmbLoRA by 32.72 percentage points. Ordinary refusal SFT achieves higher correct abstention at greater regression cost. Code and reproduction materials: https://github.com/ModeLiberaL/ReFrain.
System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectories or textual responses. Recent evaluations cover diverse tasks but often rely on existing benchmarks, where prior exposure to test material can obscure generalization. Moreover, real-world decision making often involves long contexts, large option spaces, and complex logical dependencies, challenges that existing benchmarks do not adequately capture together. Thus, we introduce MMDM (Massive Multitask Decision Making), a benchmark of 5,448 high-quality questions across 16 task categories, combining newly constructed tasks with source-grounded recompositions and rewrites for single-select, multi-select, and soft-label decision making in fresh contexts. It covers realistic scenarios such as agent state tracking, tool and skill selection, preference judgments, and rubric scoring, with option spaces ranging from 2 to 1,024 and inputs extending to 64,817 tokens. With MMDM, we conduct a comprehensive quantitative evaluation of 28 decision models, showing that many perform well on common knowledge yet struggle with interdependent options, constrained decisions, and multi-select tasks. For example, Perplexity Decider-V1.2 reaches 78.75% Hard Single-select Accuracy on world knowledge, but only 53.95% on option logic and 47.95% on constraint planning, while the best Hard Multi-select Accuracy across all models is 36.81%. These results highlight joint reasoning, constraint-aware selection, and complete multi-select recovery as key priorities for decision model development, with MMDM providing a testbed for measuring this progress.
Politically biased AI can shift users' opinions, yet it remains unclear whether model disclaimers protect against such persuasion. We report a preregistered experiment (N=1,586) examining how disclaimer design and user characteristics shape susceptibility to politically biased AI. We varied whether disclaimers identified political bias versus potential inaccuracies and whether they included an explanation. Participants completed two decision-making tasks with an LLM biased against their political views, with outcomes assessed immediately and one week later. Disclaimers identifying political bias and including an explanation reduced persuasion, but effects varied across contexts and did not persist. Individual differences were more consistent predictors: Republicans were more persuaded and reported higher trust than Democrats across tasks. Similarly, participants who used AI more frequently were also more persuaded, whereas those with greater self-reported AI knowledge were less persuaded. These findings suggest that generic disclaimers are not enough: effective safeguards must account for user heterogeneity and context.
Streaming multi-reference video generation establishes a scene from specified people and objects, then continues it under changing instructions. We introduce TaoMate-R1, a streaming multi-reference generator that organizes adaptation parameters through temporal role specialization. It assigns separate low-rank adapters to scene establishment and continuation on a frozen backbone. Each adapter performs both denoising and context writing for its role; Self Gradient Forcing jointly trains the roles through the history they construct. This allocation contrasts with operation-based specialization, which separates denoising from context writing across all chunks. A fixed-replay gradient analysis characterizes the update directions admitted by the two sharing schemes. On 32 multi-reference cases, we compare the schemes at the same two-adapter budget. Across ten approximately two-minute streams with changing instructions and shared teacher-audio conditioning, TaoMate-R1 reduces the mean boundary luminance jump from 1.96 to 0.613, with higher boundary feature similarity. It also achieves higher mean CLIP and DINO temporal similarity across short interactions, long streams, and public reference compositions. These results support grouping adaptation parameters by scene establishment and continuation for streaming multi-reference generation. Our code and model are released at https://github.com/TaoLiveAIGC/TaoMate-H3.
Many open mixture-of-experts (MoE) language models train with Muon instead of AdamW. Most balance the load with a bias on each expert's routing score, adjusted after every step. Their recipes disagree on whether Muon should also train the router. In models with 55M and 108M active parameters, we measure how the optimizer changes the span of these biases, the largest minus the smallest in a layer. The span grows when all tokens favor the same experts, so it shows how hard a layer is to balance. At learning rates tuned on shorter runs, Muon raised the span of the first MoE layer at every seed, roughly doubling it on average, while the other layers changed much less. The rise came from Muon on the rest of the network, whichever optimizer trained the router. In those runs, the inputs to the first router shared a direction, and soon after the warmup its busiest expert averaged four to seven times its fair share. Over the first 3,000 steps, subtracting the batch mean from these inputs removed this overload while barely changing the loss. On the smaller model, halving Muon's learning rate removed most of the rise and slightly improved the loss. Moving only the router to AdamW made the loads shift more during the warmup and slightly raised the loss, so at this scale the results favor keeping the router on Muon.
Unified Panoramic Geometry Estimation via Multi-View Foundation Models
Vukasin Bozic, Isidora Slavkovic, Dominik Narnhofer, Nando Metzger, Denis Rozumny, Konrad Schindler, Nikolai Kalischek
AI 速读 基于摘要
PaGeR 将面向透视图像的 3D 重建基础模型扩展到全景域,用单次前向同时预测尺度不变深度、度量深度、表面法线与天空掩码。
cs.CV · cs.AI
查看原文摘要
Geometry estimation from perspective images has greatly advanced, maturing to the point where off-the-shelf foundation models are able to reconstruct 3D scene structure not only from multi-view imagery, but even from a single view. A natural extension is 3D reconstruction from panoramas, with the exciting prospect of recovering a full 360-degree scene from a single panoramic image. In this work, we introduce PaGeR (Panoramic Geometry Reconstruction), a framework to lift powerful 3D foundation models designed for perspective imagery to the panorama domain. Our strategy is to start from a pre-trained transformer for 3D reconstruction and turn it into a unified high-performance model that predicts scale-invariant depth, metric depth, surface normals, and sky masks from both perspective and omnidirectional images, in a single forward pass. By keeping architectural changes to a minimum and mixing perspective and panoramic images during training, PaGeR retains the rich 3D prior of the underlying foundation model while learning to also estimate geometrically consistent 360-degree scenes from single panoramas. We extensively test our method in both indoor and outdoor environments and find that it delivers state-of-the-art performance and excellent zero-shot performance across a wide range of scenes. Code, data and models are available $\href{https://github.com/prs-eth/PaGeR}{\text{here}}$.
We describe SCARAB--Swarm-Capable Autonomous Robotic Aquatic Bridging. Using distributed swarm control and multi-model sensing of agents and docking targets, agents can localize themselves, join into formations and proceed to desired target locations. Our technologies would eventually allow the Army to perform unpredictable, dispersed river crossings, enhance crew survivability, and minimize the logistics footprint compared to the current Improved Ribbon Bridge. Our methods operate without GPS or RF communications, though these can be used in non-contested environments (e.g., civilian disaster relief for flooding, etc.). We demonstrate our system via physics-engine-based simulation of several agents using unmanned surface vehicles (USVs) in the presence of currents and wind.
Adversarial risk analysis (ARA) informs decision-makers when facing intelligent opponents and uncertain outcomes, enabling an analyst to model beliefs about the opponents' preferences, capabilities, beliefs, and the strategic calculations that opponents employ. Major applications cover reliability and risk analysis of critical infrastructures in presence of adversarial threats. In such domains, ARA mitigates typical common knowledge assumptions of standard game-theoretic approaches. However, ARA entails complex modelling and computations. To alleviate these, we explore its combination with fully probabilistic design (FPD), a control theory methodology supporting an agent in choosing the decision distribution that achieves the outcomes with a distribution closest to its ideal. We use FPD to model and forecast the opponent's decisions within an ARA setting and present how to handle security games within this ARA-FPD framework, covering both single and multiple stage problems.
Tushar Tyagi, Aditya Raghavan, Haoran Qiu, Francisco Romero
原文摘要
Vision-language models (VLMs) enable natural language video retrieval, bypassing traditional hand-engineered pipelines. Integrating agentic reasoning frameworks (e.g., ReAct) further advances this paradigm by allowing models to dynamically inspect video content rather than relying on a single visual pass. Applying this pattern naively to video retrieval inherits problems that video systems cannot afford: results vary from run to run under identical conditions, and cost and latency scale with every reasoning step the agent takes rather than with the work the query actually requires. We present VASTRA, an agentic video retrieval system whose execution is dictated by query complexity rather than an open-ended reasoning loop: cheap, reliably answerable queries are ranked directly from pre-ingested summaries, while harder queries trigger targeted verification only where relevance is genuinely uncertain. This keeps control flow external to the model rather than latent in a growing chain of thought, establishing deterministic control flow by construction and end-to-end rank reproducibility under greedy serving. Across 40 benchmark queries, VASTRA exposes explicit presets: VASTRA-Fast runs 12.2x faster (4.2 s vs. 51.2 s) and 10.4x cheaper ($0.0044 vs. $0.0458) than best performing ReAct agent at a 5.0-point mAP reduction, while VASTRA-Max matches peak ReAct agent accuracy (0.653 vs. 0.649 mAP) at comparable latency, trading higher spend ($0.1022 vs. $0.0458) for zero run-to-run variance.
Although large language models have demonstrated strong performance on algorithmic and mathematical tasks, their suitability as social science research assistants remains unclear, particularly because many social science questions lack agreed-upon, quantifiable benchmark answers. Evaluating this suitability is important since researchers and students increasingly rely on AI to generate research ideas. When questions concern the countries in which models were developed, bias may be exacerbated: Do AI models favour the countries where they were developed or the social theories associated with those countries' scholarly traditions? Such biases could distort research findings, undermine scientific credibility, and distort findings when they are disseminated to the public. To investigate whether models exhibit country-focused bias in social science research, we designed a benchmarking task requiring AI to write short essays on social science questions in relation to the US and China as well as some broader social science questions. We varied three conditions: question type (cross-country comparisons, country-specific questions, and general questions); model (two US-developed, two China-developed, and one Europe-developed model); and prompting modality (a base essay-writing request, a researcher identity, a US researcher identity, and a Chinese researcher identity). Responses were manually annotated for bias and source use by two researchers with experience in social science in relation to China and the US. Our analyses show that, on the whole, US and Chinese models and the European one are not politically biased but differ in the sources they cite. Still, some comparative questions favour one country over another, and this tendency is more pronounced for certain questions. These findings suggest that researchers and students should exercise caution when using AI for social science research.
Generative driving planners can represent diverse ego futures, but a downstream scorer can choose only among sampled candidates; it cannot recover an absent maneuver. We present ForeseeDrive, which turns future scene evolution into a deployable interface for shaping candidate generation. Rather than reconstructing dense future states or scoring a fixed menu, ForeseeDrive derives query-indexed tokens from logged actor motion, occupancy evolution, route interactions, and TTC margins, and predicts the same token space from present context at deployment. The tokens condition trajectory geometry before candidates materialize. A zero-token-gated residual path and candidate-preservation loss limit unnecessary drift, while a TTC-margin guard targets brittle safe-to-unsafe boundary crossings. Under their respective benchmark protocols, ForeseeDrive reaches 89.2 PDMS on NAVSIM navtest, 0.41\,m average L2 and 0.05\% collision rate on nuScenes validation, and a 76.50 driving score on Bench2Drive. Controlled DiffusionDrive/NAVSIM diagnostics show an exact zero-token no-op, a small aligned-over-shuffled selected-PDM advantage under preservation, mixed oracle-best quality, and localized TTC-boundary failures. Together, the benchmark results and bounded mechanism tests support future-conditioned generation as a practical interface for anticipation. Code is included in the supplementary materials.
Evaluating candidate parallelization strategies through distributed training runs makes strategy selection prohibitively expensive at scale. Performance simulation offers a lower cost alternative, yet controlled comparisons among existing simulators remain difficult because they differ in the training stages they model and the workloads on which they are evaluated. We introduce LM-SimBench, a unified framework, profiling dataset, and benchmark for evaluating LLM training simulators. The framework decomposes simulation into functional stages from model compilation to schedule level aggregation, connecting execution representations and cost estimators to measurable evaluation targets. Following this framework, we profile 23 model settings from 10 dense and Mixture-of-Experts (MoE) LLM families on an Ascend Neural Processing Unit (NPU) cluster. The resulting dataset contains 348 feasible configurations that jointly vary five parallelism dimensions and activation recomputation, with six views spanning configuration, rank, operator, event, and kernel granularity. Evaluations of representative training simulators demonstrate how LM-SimBench supports comparisons of prediction accuracy, assessment of configuration selection, and diagnosis of prediction errors. Matched GPU-NPU experiments validate the cross-platform applicability of the collection and evaluation protocol and demonstrate NPU-guided GPU configuration selection.
Worst-case complexity bounds often fail to reflect the practical performance of optimization algorithms, while average-case complexity heavily relies on the distribution of the input. In this work, we develop a smoothed-analysis framework for classical continuous optimization algorithms by studying their behaviour on random perturbations of arbitrary functions. Our main contribution is to apply methods suited for non-degenerate functions to perturbations of degenerate functions, thereby recovering the faster best-known rates for the non-degenerate class. We derive smoothed complexity guarantees for several standard methods, including (Accelerated) Gradient Descent, Conjugate Gradient, and Newton-type methods, under various settings including nonconvex ones, and show that these bounds can substantially improve upon their worst-case guarantees, bringing them closer to the practical behaviour of the respective methods.