Machine Learning
Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
Walid Bendada and Guillaume Salha-Galvan
Sampling from a softmax distribution is a fundamental operation in machine learning, but its linear complexity in the number of items makes exact sampling impractical at scale. Two-level softmax (2LS) sampling is a popular alternative enabling sublinear-time sampling. Assuming items are partitioned into clusters, 2LS first samples a cluster and then an item within it. In this paper, we show that, despite its advantages, 2LS introduces systematic and undesirable sampling biases, which arise from misweighting clusters by ignoring both cluster size imbalance and intra-cluster similarity dispersion. We propose two sampling methods, Size-Corrected 2LS (S-2LS) and Size- and Dispersion-Corrected 2LS (SD-2LS), which correct these biases and provide provably better softmax approximations with negligible to non-existent computational overhead. In-depth experiments on five large-scale
datasets validate the improved sampling properties of our methods. We recommend their consistent use in place of standard 2LS in future work.
Read the full abstract ▾
Numerical Analysis · Cross-listed from math.PR
Random permutations using GEPP
Kenji Gunawan, John Peca-Medlin and Chenyang Zhong
Gaussian elimination with partial pivoting (GEPP) remains the most widely used solver for dense linear systems $A \mathbf x = \mathbf b$ for $A \in \mathbb C^{n\times n}$. We study the permutation $\pi = \pi(A)$ that arises in the GEPP factorization $PA = LU$, encoded by the permutation
matrix factor $P = P_\pi$. When the input
matrix is random, so is $\pi$. For random scalar butterfly
matrices of size $2^n$ (a recursively defined family originally introduced to eliminate the need for pivoting altogether), we give the exact GEPP factorization and fully classify the induced permutation as an element of a $2$-Sylow subgroup of $S_{2^n}$ contained in the separable permutations. Moreover, the uniform-angle model induces the uniform distribution on this subgroup. For the GOE, GUE, and iid Bernoulli models, the induced permutation is never exactly uniform for $n \ge 2$. We give the precise rate of departure from uniformity at the leading pivot for the GOE and GUE, and give evidence that this non-uniformity vanishes asymptotically in the permuton sense. In contrast, for banded random
matrices of sublinear bandwidth, including the tridiagonal $\beta$-Hermite ensembles, the induced permutation converges to the diagonal permuton. We further show that the resulting pivot probabilities are sensitive to implementation choices: standard LAPACK routines compare complex pivot candidates using the $\ell^1$ rather than $\ell^2$ norm, changing the GUE(2) pivot probability from $1/\sqrt3$ to $2/3$. Together these results establish a new connection between random
matrix theory and permutation combinatorics through numerical linear
algebra.
Read the full abstract ▾
Robotics
Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies
Yihan Li, Yating Feng, Shengjiu Sun et al. (+7 more)
A simulation of a real
robot workspace must preserve task-relevant interactions, while policies developed in it must operate on observations available to the real
robot. Yet scene reconstruction and policy development are often treated separately. We present Agentic Real-to-Sim-to-Real (Agentic RSR), a framework that links scene reconstruction, policy development, and real-
robot execution through the same manipulation task. Given a workspace
video, a task description, and a known
robot model, an
agent recovers metric scale, iteratively refines the scene using visual feedback, and checks task-relevant interactions in MuJoCo. A coding
agent then develops an executable policy, progressing from privileged object poses to visual observations and randomized simulation. The policy can interleave multiple observations and actions within one invocation, while the
agent uses execution feedback to continue, retry, or revise its approach. A shared task-level interface carries the policy and accumulated experience to the real
robot, where fresh observations and safety checks guide execution. Using Claude Opus 5.5 through DeepSeek Harness (DSH), all 18 scenes across two
robots pass the joint visual check; mean four-view Depth MAE against reference depth estimates is 0.0808 m, mean Lab $\Delta E_{76}$ is 8.01, and mean grayscale SSIM is 0.7338. In real-
robot experiments, the aggregate task success rate reaches 80% of the simulation task success rate, indicating substantial retention of simulated performance on hardware. Code and reconstructed scene data will be made publicly available.
Read the full abstract ▾
All authors Yihan Li, Yating Feng, Shengjiu Sun, Jianing Chen, Hao Ren, Bowen Yang, Weisheng Xu, Qiwei Wu, Hui Cheng, Renjing Xu
Artificial Intelligence
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
Tan Yu, Alexander Bukharin, Khushi Bhardwaj et al. (+19 more)
How can we predict which base checkpoint is worth an expensive round of agentic post-training? End-to-end pass@$K$ tests whether successful behavior already appears in a base model's distribution, but it is a poor fit for agentic coding: many base checkpoints cannot reliably produce the well-formed tool invocation required to complete a task end-to-end. Single-shot or short-horizon tasks avoid these tool-calling failures by collapsing a multi-step interaction into a fixed
prompt and a single patch, but they sidestep the core capability we care about: maintaining coherent state over many tool-using steps as the repository evolves. To bridge this gap, we treat successful post-trained
agent trajectories as a lookahead signal of base-model potential. Replaying each trajectory and rerunning tests after every code-changing step identifies the decisive step: the first step whose cumulative patch flips the repository from failing to passing, certifying that the recorded action solves the task given the prior context. Motivated by a coverage principle for agentic traces, we build three screens at this step that do not require a base checkpoint to drive the harness from a cold start: (i) Decisive-Action BPB (bits per byte) measures the probability mass on the certified action, (ii) Patch MCQ tests the checkpoint's choice between that action and alternatives rejected by the same verifier, and (iii) prefix-conditioned pass@$K$ evaluates support for functionally-correct generations and credits any continuation that the tests accept. Across ten pairs of public base and post-trained models, all three screens rank the cohort in close agreement with post-trained SWE-bench Verified pass@$1$. As our methods need only a
benchmark's successful trajectories and its verifier, they can be applied to turn future agentic coding
benchmarks into base-model evaluations.
Read the full abstract ▾
All authors Tan Yu, Alexander Bukharin, Khushi Bhardwaj, Jennifer Williams, Zirui Liu, Jonathan Lingjie Li, Soumye Singhal, Joseph Jennings, Sanjeev Satheesh, Yash Jain, Ashish Vaswani, Venkat Krishna Srinivasan, Matthew Papakipos, Hyunwoo Kim, Jian Zhang, Oleksii Kuchaiev, Markus Kliegl, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jonathan Cohen, Jiantao Jiao
Computational Complexity
Primal/Dual Method for the Grothendieck Constant
Steven Heilman, Chris Jones and Giulio Malavolta
We determine the hundredths digit of the real Grothendieck constant by proving $1.773 \leq K_G \leq 1.7799$. Furthermore, numerical heuristics suggest the estimate $K_G \approx 1.779$. We start by simplifying the Gaussian duality theory of $K_G$, based on Hermite projection games and Krivine rounding schemes. The bounds are obtained by a heuristic primal/dual search for these objects, followed by rigorous certification of their values. The search and certification are performed using AI tools, and in particular the rigorous certificates are very large (analytical reductions to thousands of numerical inequalities).
Read the full abstract ▾
Data Structures and Algorithms
Fast Almost-Uniform Sampling of Random $k$-SAT Solutions
Kun He, Zhidan Li and Kuan Yang
We study approximately uniform sampling of satisfying assignments from random $k$-SAT formulas. For every sufficiently large $k$ and density $0 < \alpha \le 2^k/k^{16}$, we prove that, with high probability over the formula, there is a sampler whose output distribution is within total variation distance $\varepsilon$ of the uniform distribution on satisfying assignments and whose expected running time is at most $(nk(\alpha+1)/\varepsilon)^C$, for a universal constant $C$. Our
algorithm improves the counting and sampling
algorithms obtained by Chen, Lonkar, Wang, Yang, and Yin (STOC 2025) at the density $2^k/\operatorname{poly}(k)$ with running time $(n/\varepsilon)^{\operatorname{poly}(k,\alpha)}$. Our result achieves this density region for sampling with a
polynomial degree independent of both the width and the density. Our
algorithm separates a high-degree core from the remaining variables, and combines a recursive sampler for the residual formulas with approximate block heat-bath updates on the core. We adapt the recursive insertion-chain framework of Jain, Mizgerd, and Pham (2026) from $2$-trees to ordinary connected violation sets. Expansion and random literal signs yield uniform moment bounds for the resulting correlated lists across all residual formulas, allowing the signed-flow analysis to give a universal
polynomial running-time degree. A
polymer expansion and an exploration bound establish a
polynomial spectral gap for the core dynamics.
Read the full abstract ▾
Computer Vision
Label-free cell counting and viability prediction with brightfield imaging and deep learning
Amir Reza Vazifeh, Christian Zeigler, Sornanathan Meyyappan et al. (+2 more)
Cell viability assessment is a core requirement in
cell culture systems, with critical applications in biopharmaceutical manufacturing and drug development. Conventionally, it is measured by adding membrane-impermeable dyes to a sample (a process called staining), which allows compromised
cell membranes to be distinguished from intact ones. However, staining has several limitations: (a) chemical
agents can perturb normal cellular processes of the
cells being measured, (b) it is often ambiguous to assign viability to individual
cells whose membrane integrity is only partially compromised. (c) photobleaching can undermine measurement accuracy over time when using fluorescent stains, and (d) staining cannot be performed in situ or in real time. Here, we show that (1) stained
cells captured under brightfield imaging contain sufficient information to distinguish live and dead
cells, and (2)
cells captured under unstained brightfield imaging exhibit similar image features to their stained counterparts, enabling models trained on stained
cells to generalize to unstained ones. We then report the development and validation of ViabiLens, an AI-assisted software for label-free
cell viability analysis. The ViabiLens combines a
cell detection model for localizing individual
cells with a convolutional neural network (CNN) classifier for live/dead prediction, paired with an interactive UMAP-based viewer for visualizing and exploring individual
cells across the sample. Evaluated on Chinese Hamster Ovary (CHO)
cells spanning a wide range of viability conditions, ViabiLens achieves a mean absolute error of 2.68% on unstained samples against fluorescence-based reference measurements. We also release a
benchmark dataset for label-free
cell viability analysis to facilitate future research, available at https://amirrezavazifeh.github.io/ViabiLens-Project-Page/.
Read the full abstract ▾
All authors Amir Reza Vazifeh, Christian Zeigler, Sornanathan Meyyappan, Richard Jeske, Jason W. Fleischer
Robotics
Robotic Boomerang Throwing via Model-Based Release Design
Yang Liu, Colin Jones and Aude Billard
Throwing objects that generate aerodynamic lift can greatly extend
robot throwing beyond ballistic flight. A returning boomerang is a challenging example because its flight depends strongly on the release velocity, attitude, and
spin, while robotic manipulators cannot readily reproduce the rapid motions used in human throwing. We present a model-based framework for robotic boomerang throwing centered on the release state. We identify the boomerang flight dynamics in stages to predict how flight changes across design variations. To systematically design the
robot throwing motion, we screen candidate parameters according to how strongly and consistently they control release
spin under uncertain contact conditions. These models are then used to design the throwing motion and boomerang for a 6-DoF manipulator with limited joint speeds. To our knowledge, this is the first robotic manipulator to generate a returning boomerang flight. In the demonstrated returning trial, the boomerang is released at 51 rad/s (8.1 rev/s), reaches 2.03 m from the
robot base, and returns to touch down 0.31 m from the base. The successful release differs significantly from the measured human throws, showing that a
robot need not imitate human throwing motion to achieve a returning flight. The project page is available at https://
robot-boomerang.github.io
Read the full abstract ▾
Robotics
CMP-IRRT*: A Perception-Assisted Height-Adaptive Planner for Quadruped Robots
Mingfan Zhao, Wendong Mao and Zhongfeng Wang
Quadruped
robots can traverse low obstacles, but many 2D planning pipelines still model obstacles as binary occupied regions and rely on sampling-based search that can be inefficient under a limited budget. We propose a perception-assisted height-adaptive planning framework based on CMP-IRRT*, a Channel Mamba PointNet-guided Informed RRT* planner. Given a calibrated top-view RGB observation, the perception module estimates obstacle regions and converts depth predictions into a ground-relative height map. The planner then performs height-conditioned collision checking, treating high obstacles as blocked while allowing low obstacles to be traversed, and uses the CMP guide to bias sampling toward promising regions while retaining standard free-space and informed sampling fallbacks. Experiments on 2D planning
benchmarks show that CMP-IRRT* reduces explored nodes and iterations compared with classical and neural-guided baselines, and a controlled ablation supports the contribution of the Mamba-based guide. In constructed traversability-aware scenarios, the proposed planner reduces path length by up to 16.3% when low obstacles are traversable, and a Unitree Go2 demonstration further shows executable bypassing and traversal behaviors. Our code is publicly available at https://github.com/MingfanZhao/height-adaptive-planner.
Read the full abstract ▾
Multiagent Systems
A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
Ali Asaria, Deep Gandhi and Tony Salomone
Deployments of research
agents are moving to populations of thousands that share one pool of compute, while most current systems organize one project at a time or leave the population unorganized. We argue that such a population will acquire an organization whether or not its designers provide one, so designers should provide it explicitly, and that the multi-
agent systems community holds the tools to do so. We propose a society of
agents, a population of persistent
agents under explicit institutions, and develop it for science as a society of researchers built on six principles. Principal investigators compete for compute through requests for proposals, independent review, and grants; a human governor, the mayor, allocates resources and assigns no tasks. In a running society of ten thousand researchers, asked only to improve the pretraining of
language models, one lab reported a way to reach the same quality with about 30% less compute, a result the labs that tested it do not yet agree on. We close with six open problems for the
agents community.
Read the full abstract ▾
Information Theory
Polarforming for MIMO Covert Communications
Xin Xie, Jinpeng Xu, Yihang Huang et al. (+2 more)
Covert communication conceals wireless transmission activity, but conventional multi-
antenna designs rely mainly on spatial beamforming and can be constrained by limited spatial degrees of freedom. This paper investigates polarization-reconfigurable
antenna (PRA)-aided multiple-input multiple-output (
MIMO) covert communication, where Alice and Bob perform transmit and receive polarforming, respectively, and Willie uses a vertically polarized
antenna for radiometric detection. We jointly optimize the transmit covariance
matrix and the transmit and receive phase shift vectors to maximize Bob's achievable rate under the covertness and transmit power constraints. Under Gaussian signaling, perfect polarized channel state information, and known noise power at Willie, we derive his optimal radiometric threshold and exact minimum detection error probability (DEP) for a finite observation length, and convert the DEP requirement into a deterministic constraint on his received signal power. We further prove that, for a fixed transmission design, positive signal leakage becomes detectable as the observation length tends to infinity. To solve the design problem for a finite observation length, we develop an alternating optimization (AO)
algorithm with a generalized water-filling covariance update and closed-form phase updates. Numerical results validate the exact DEP analysis and the rapid convergence of the proposed
algorithm. Compared with the sufficient divergence-based condition, the exact covertness constraint permits a $0.99$–$1.12$~dB higher received signal-to-noise ratio (SNR) at Willie, while joint transmit and receive polarforming provides a rate gain of up to $53.8\%$ over the considered
benchmark schemes.
Read the full abstract ▾
All authors Xin Xie, Jinpeng Xu, Yihang Huang, Li Zhou, Zhaolong Ning
Robotics
LLA-MPPI: Rapidly Adaptive Whole-body Control of Legged Robots with GPU-Accelerated Parallel Simulations
Sebin Jung, Maitham F. AL-Sunni, Juan Alvarez-Padilla et al. (+3 more)
Real-time whole-body controllers for legged
robots typically plan through a fixed nominal model and degrade when the deployed dynamics change. Adaptive methods typically require a model structure that contact dynamics do not provide, or they need offline training for each anticipated condition. We present Look-back and Look-ahead Adaptive Model Predictive Path Integral control (LLA-MPPI). The method converts whole-body adaptation into selection over a bank of GPU-batched contact simulators with different physical or structural parameters. Windowed prediction errors select the simulator that best explains recent motion. A whole-body MPPI planner optimizes controls through the selected model. The framework requires no offline training, and its selected hypotheses are physically interpretable. Across four simulated tasks, it achieves 97.5% success while the strongest baseline reaches 74% and an oracle with the true model reaches 98.5%. Hardware validation on a Unitree Go2 shows the
robot walking under a payload added mid-run, walking after one leg is disabled, and pushing a box to its goal while increasing its mass on the fly. Code,
videos, and project details are available at: https://lla-control.github.io
Read the full abstract ▾
All authors Sebin Jung, Maitham F. AL-Sunni, Juan Alvarez-Padilla, Zachary Manchester, Changliu Liu, John M. Dolan
Human-Computer Interaction
How assigned AI use before class shapes active student engagement in class
Dan J. Wang, Neelam Modi Jain, Vanessa Burbano et al. (+5 more)
AI learning tools are rapidly entering classrooms, but evidence about whether they help students learn is mixed and rests mostly on test scores. Comparatively less research addresses whether the use of AI changes students' live learning behaviors in class. Here, we report the results of a preregistered field experiment with 759 MBA students enrolled in ten sections of a course, in which each student was randomly assigned two of ten class sessions to prepare for with a purpose-built voice-based AI discussion partner. After two uses of the AI discussion partner, students made about 31% more voluntary contributions in each later class session. Students who used the AI discussion partner more also reported greater comfort speaking up and greater perceived learning, but not greater focus or motivation. These findings suggest that repeated practice with a voice-based AI partner can meaningfully increase students' engagement in class discussion, enhancing a critical intermediate learning outcome.
Read the full abstract ▾
All authors Dan J. Wang, Neelam Modi Jain, Vanessa Burbano, Jorge Guzman, Daniel Keum, Soomi Kim, Bruce Kogut, Nataliya Wright
Robotics
FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding
Lipeng Zhuang, Shiyu Fan, Yingdong Ru et al. (+4 more)
We present FoldBack, a self-correcting masked generative policy for long-horizon garment folding. Existing long-trajectory policies may continue after a missed or slipped grasp even when the garment has not reached the intended configuration. We structure FoldBack's recovery mechanisms around three inference-time decisions: when to refine and verify, how to roll back, and where and how to retry. FoldBack aligns refinement and grasp verification with pick-and-place events, returns the
robot to a retryable pre-grasp configuration while preserving successful grasps, and selectively regenerates the failed segment and selected future actions while avoiding previous failed grasp locations. To our knowledge, FoldBack is the first editable full-trajectory policy to unify these decisions, enabling failed interactions to be detected, undone, and repaired before execution continues, without recovery demonstrations or base-policy retraining. Across 33 real garments from six categories, FoldBack achieves 75.2% final folding success and 0.837 final-mask IoU, versus 45.7% and 0.689 for the strongest prior baseline.
Read the full abstract ▾
All authors Lipeng Zhuang, Shiyu Fan, Yingdong Ru, Zhuo He, Florent P. Audonnet, Paul Henderson, Gerardo Aragon Camarasa
Machine Learning
Composing What Each Teacher Learned: Delta Distillation for Multi-Teacher On-Policy Learning
Yuanda Xu, Hejian Sang, Zhengze Zhou et al. (+4 more)
Multi-teacher on-policy
distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one
prompt domain and their signals form a single target; in routed-domain
distillation,
prompts from different domains are assigned to the corresponding specialist. Both settings usually transfer each teacher's endpoint policy, which mixes what post-training changed with preferences inherited from the teacher's base. We introduce $\Delta$-MOPD, which transfers each teacher's teacher-minus-base logit shift re-anchored at the student's frozen initialization, and compare it with endpoint supervision in both settings while holding teacher selection fixed. We first expose the mechanism that impedes endpoint transfer: inherited base pull can exceed the post-training shift. Removing it reduces the teacher-term norm ratio and target–student KL. Across our experiments, the results suggest that shift targets are particularly useful when teacher signals are combined at a state. With three composed teachers, $\Delta$-MOPD exceeds endpoint composition by $4.11$ Math and $1.95$ five-
benchmark points; with two, it matches endpoint accuracy. Under phased routing, it achieves higher mean performance in both phase orders and reduces the observed order gap from $10.50$ to $6.42$ points. Under interleaved routing, where each update involves one teacher, the two targets perform comparably. The phased results provide supporting evidence that the benefit may extend to signals accumulated across training phases. Target construction is thus an independent design axis in MOPD, complementary to teacher selection. The experiment repo could be find at https://github.com/HJSang/Delta-MOPD
Read the full abstract ▾
All authors Yuanda Xu, Hejian Sang, Zhengze Zhou, Shayan Mohajer Hamidi, Xiaomin Li, Rohit Jain, Alborz Geramifard
Machine Learning
NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy Modeling
Ting-Yu Dai, Takuya Kurihana, Wing Yee Au et al. (+1 more)
Demand-side flexibility i.e.
forecasting, shifting, and curtailing residential energy loads, depends on thermal models trusted across millions of heterogeneous buildings. Existing tools force a hard tradeoff: high-fidelity physics simulators such as EnergyPlus are accurate but sequential and require per-building calibration, while purely data-driven sequence models scale but abandon the physical structure that makes their predictions trustworthy. We introduce NeuralBES (Building Energy Simulation), a differentiable emulator that resolves this tradeoff by parameterizing a resistance–capacitance (RC) based thermal model with a shared neural encoder: static building metadata such as floor area, vintage, and HVAC type is mapped to physically bounded capacitances, conductances, and equipment coefficients, which become the coefficients of a scalar linear recurrence solved via a log-space parallel scan, and a predictor–corrector loop closes the thermostat–temperature nonlinearity while preserving full-horizon gradient flow. Trained on the ResStock
dataset across three
climate zones, NeuralBES handles heterogeneous building archetypes, vintages, and
climate zones within a single trained encoder, while black-box baselines produce statistically plausible but physically inconsistent trajectories. On the annual full-year rollout, NeuralBES is the only data-conditioned model that is simultaneously physics-valid and accurate to within 4 MAPE points of the strongest raw-error baseline, while operating at roughly an order of magnitude fewer parameters than the
transformer and recurrent baselines; among physics-valid baselines at parameter parity it more than halves the MAPE of the grey-box RC alternative.
Read the full abstract ▾
All authors Ting-Yu Dai, Takuya Kurihana, Wing Yee Au, Hon Yung Wong
Computer Vision
MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion Acceleration
Yuxiang Xiong, Ruiyan Wang, Wenqiang Wang et al. (+5 more)
Diffusion Transformers (DiTs) achieve remarkable performance in
video synthesis, but their iterative denoising process suffers from high inference latency. To address this, caching has emerged as an effective acceleration strategy by capitalizing on inter-step redundancy during denoising. Existing dynamic caching methods typically estimate the error that cache reuse would introduce at each denoising step (step error) to guide cache decisions, whereas our concern is how much quality loss cache reuse would cause in the final generated
video (terminal error). We show that step error does not directly correspond to terminal error and that latent information helps capture their relationship, thereby informing cache decisions. Moreover, existing threshold-based methods cannot provide precise speedup control, making it difficult to meet practical requirements for user-specified acceleration targets. To address these limitations, we introduce MORCA, a cache scheduling framework trained through offline-to-online reinforcement learning to make latent-aware reuse/recompute decisions under user-specified acceleration targets. Extensive experiments on different
video generation models across multiple target acceleration ratios demonstrate that MORCA achieves better generation fidelity than state-of-the-art caching methods under comparable computational budgets. Code is available at https://github.com/x10ngyx/MORCA.
Read the full abstract ▾
All authors Yuxiang Xiong, Ruiyan Wang, Wenqiang Wang, Teng Hu, Songhang Shen, Bohao Feng, Hongqian Deng, Ran Yi
Game Theory · Cross-listed from econ.TH
Risk-minimizing GUE-implementations of truthful reporting in a Dynamic Social Choice Problem
Endre Csóka and Máté Viczián
The Guaranteed Utility Mechanism (GUM) was introduced to implement efficiency in Guaranteed Utility
Equilibrium (GUE) in dynamic social choice problems. We show that this mechanism also has a previously unknown connection to risk minimization. Fixing an efficient decision policy, we study variance-minimizing budget-balanced transfer rules in the class of GUE-implementations of truthful reporting. A symmetrized version of GUM (sym-GUM) minimizes the sum of the
agents' utility variances under truthful reporting when there is no public state. When a public state is present, a slight modification of this rule yields the minimizer for the same objective. Sym-GUM, however, does not minimize transfer risk. The minimizer for that problem is instead the symmetrized version of a closely related GUM-like transfer rule. In both problems, the minimizing truthful total transfers are unique up to
agent-specific constants summing to zero and events of probability zero.
Read the full abstract ▾
Computation and Language
PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
Linghao Meng, Feng He, Xuan Yang et al. (+5 more)
Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent
reasoning. Existing studies of post-
hallucination reasoning (PHR) mainly characterize changes in final outcomes and aggregate
reasoning dynamics, leaving how models resolve hallucinated premises at the response level insufficiently understood. In this work, we introduce PHRBench, a controlled
benchmark for behaviorally structured PHR across four domains and 18 large
language models. PHRBench characterizes each
reasoning trajectory independently of final-answer correctness through
Hallucination Compliance,
Hallucination Avoidance, and Heuristic Correction, and defines an insightful trajectory as successful correction that ultimately reaches the correct answer. Across 4820 controlled instances, we find that successful recovery remains relatively rare and is associated with more frequent belief updates along the
reasoning trajectory. We further find that properties of the hallucinated
prompt contain substantial predictive signal for successful recovery, with a lightweight predictor achieving an AUROC of 0.847. These findings provide a behavioral view of post-
hallucination reasoning, characterizing how LLMs resolve erroneous context and when successful recovery is likely to occur.
Read the full abstract ▾
All authors Linghao Meng, Feng He, Xuan Yang, Junyuan Mao, Pinze Ren, Deqing Mu, Hesen Yang, Qiankun Li
Robotics
RFPO: Rectified Flow Policy Optimization for Embodied Control
Ting Huang, Lisiyu Pan, Haoyu Wang et al. (+6 more)
Flow-based policies provide an expressive framework for continuous
robot control, but their iterative ODE integration incurs substantial inference cost. Naively reducing the integration budget can severely degrade control, since policies optimized under full-step execution are not explicitly constrained to remain reliable under coarse numerical integration. We refer to this mismatch as the few-step discretization gap. To address this problem, we introduce RFPO, a flow-policy optimization framework for reliable few-step execution. Reward-aware online Reflow rectifies student-induced transport paths during on-policy learning, making the resulting policy more robust to coarse integration. A frozen Gaussian PPO controller supplies complementary action-space supervision at full and intermediate integration budgets, while the deployed policy remains a single flow student executed with one Euler step. Across Unitree Go2, Boston Dynamics Spot, Unitree H1, and Unitree G1, RFPO consistently preserves full-step control performance under one-step execution, with one-step returns remaining within 2.4% of their corresponding 64-step values across both zero and random initialization. On Unitree Go2, one-step execution retains 98.5% of the 64-step reward while reducing onboard mean inference latency from 4.39 ms to 0.08 ms, yielding a 54.9x speedup. Real-
robot experiments further validate stable one-step locomotion. Code: https://github.com/AIGeeksGroup/RFPO. Website: https://aigeeksgroup.github.io/RFPO.
Read the full abstract ▾
All authors Ting Huang, Lisiyu Pan, Haoyu Wang, Zeyu Zhang, Siyuan Qian, Yanjun Li, Yandong Guo, Boxin Shi, Hao Tang
Multimedia
MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive Screening
Duy-Cat Can, Mau Minh Phuc Le, Tuan-Khoa Hoang et al. (+10 more)
MemoCare is an interactive mobile system for automated
multimodal cognitive screening. A React Native application combines spoken responses, temporal and spatial orientation, touchscreen actions, and visuoconstruction in complete English and Vietnamese workflows.
Speech is transcribed by Google
Speech-to-Text and scored locally with deterministic task-specific natural
language processing rules; GPS coordinates are resolved by the MemoCare spatial module before answer matching; touch tasks are scored from interaction events; and the drawing task uses a three-model convolutional neural network consensus with separate visual interpretation. Software tests pass 151/151 predefined cases across
speech/
language, spatial-answer, and touch-interaction scoring, while spatial regression passes 48/48 four-country coordinate-resolution cases. For the drawing module, validation-selected ShuffleNetV2 x1.5 achieved 91.33% mean balanced accuracy and 78.87% exact three-criterion accuracy on a locked 71-image test set. Four clinician co-authors additionally inspected the end-to-end workflow, yielding a pooled median rating of 4/5 across eight criteria, with item-level medians ranging from 3 to 4.5. At MMM, attendees can directly try a shortened
multimodal screening workflow and inspect automatic item-level and total scoring.
Read the full abstract ▾
All authors Duy-Cat Can, Mau Minh Phuc Le, Tuan-Khoa Hoang, Hai-Dang Nguyen, Trung-Hieu Do, Dang Minh Ly, Minh-Duc Nguyen, Nghia TT Hoang, Linh-Trung Nguyen, Huy-Hieu Pham, Huong Ha, Binh T. Nguyen, Oliver Y. Chén
Machine Learning
A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching
Randy Ardywibowo, Arnav Dalal and Jiantao Jiao
Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and costly to generate. On-Policy
Distillation (OPD) offers an attractive alternative by providing dense
token-level supervision from a stronger teacher along the student's own generations. Self-
distillation methods further remove the need for a separate teacher model by conditioning the same policy on privileged information to serve as its own teacher. However, privileged conditioning alone does not guarantee that the resulting
distillation update improves the student. Indeed, privileged information can lead the teacher to solve tasks through shortcuts unavailable to the student, producing supervision poorly matched to the student's current behavior. Consequently, even a higher-performing teacher can provide guidance that degrades student performance. To address this, we analyze how the choice of privileged teacher affects the student's update. We derive a necessary and sufficient condition for the teacher's local
distillation update to be a positive multiple of the student's reward gradient. Our analysis suggests that the teacher should not only perform well on the task, but also provide guidance suited to the student's current capabilities. This characterization motivates a practical teacher-training surrogate that combines outcome rewards with
token-level Kullback-Leibler (KL) regularization toward the student. Based on this result, we propose Joint On-Policy Learning and Teaching (JOLT), which jointly trains a single policy in two roles: a privileged teacher using a KL-regularized objective, and an unprivileged student using dense on-policy
distillation. Across mathematical
reasoning, coding, tool use, and terminal use, JOLT improves training efficiency and performance, with further gains from student rewards.
Read the full abstract ▾
Data Structures and Algorithms
Subset Sum via Partial Match
Lixi Ye and Baitian Li
We show that the subset sum problem can be solved in time $O(2^{0.499999n})$, breaking the $2^{n/2}$ meet-in-the-middle barrier. Our approach builds on the representation technique framework of Randolph and Węgrzycki (STOC 2026). We choose a representation for which testing the compatibility of pairs of partial solution vectors is exactly the partial match problem. To beat exponent $1/2$ for subset sum, it then suffices to give a nontrivial partial match
algorithm in a certain parameter regime. We achieve this by designing a depth-2 linear
circuit for the partial match
matrix, which yields an efficient
algorithm via the framework of Alman and Li (FOCS 2025).
Read the full abstract ▾
Artificial Intelligence
RunningTab: Direct Workspace Interaction with Environment-Side Tabs
Jinheon Baek, Soyeong Jeong, Yumin Choi et al. (+2 more)
Much knowledge work produces new deliverables from files a workspace already holds, and LLM
agents are beginning to take such work over. Through direct corpus interaction, an
agent can search and read any of those files from a terminal with no indexing, and producing a deliverable from many of them in this way is what we call direct workspace interaction (DWI). Reaching the files, however, is only half the task: nothing keeps track of what the task asks for, what has been read, and what was listed but never opened, all of which slip through the context window without leaving a trace, so an
agent may extract a figure and still deliver a report without it. To address this, we present RunningTab, a framework that equips direct workspace interaction with an environment-side tab: a per-task record of what the task still owes, kept by the environment alongside the
agent. Specifically, the
agent adds its requirements, while the environment records every file read as an excerpt with its provenance and every listed but unopened file as a candidate; the
agent can then see each requirement beside its best-matching excerpts and top unopened candidates, resolve it against matching content or set it aside with a reason, and, should it try to finish with requirements still open, receive them in a finish check. We validate RunningTab on three
benchmarks with three LLMs, where it consistently outperforms plain DWI and baselines that keep the record in the model, while its tab usually holds the values a deliverable needs once seen.
Read the full abstract ▾
All authors Jinheon Baek, Soyeong Jeong, Yumin Choi, Dongsu Han, Sung Ju Hwang
Data Structures and Algorithms
Color Coding for the Sherrington-Kirkpatrick Model
Alina Harbuzova, Saba Lepsveridze, Mahbod Majid et al. (+1 more)
We give a
polynomial-time
algorithm for approximating the partition function of mean-field mixed $p$-
spin models to arbitrarily high accuracy throughout the second-moment regime. This improves the quasipolynomial-time
algorithm of Bencs, Huang, Lee, Liu, and Regts (arXiv:2507.15616) and answers their open question. In particular, our result covers the entire replica-symmetric regime of the Sherrington–Kirkpatrick model. The
algorithm is deterministic, runs in time
polynomial in $n$ and $1/\varepsilon$, and succeeds for every typical realization of the disorder. Our main technical contribution is a new algorithmic application of color coding to the classical high-temperature expansion introduced by Aizenman, Lebowitz, and Ruelle in their study of fluctuations of the Sherrington–Kirkpatrick partition function. We combine this approach with the zero-freeness established by Bencs et al. (arXiv:2507.15616) to convert additive approximations into multiplicative ones.
Read the full abstract ▾
All authors Alina Harbuzova, Saba Lepsveridze, Mahbod Majid, Ankur Moitra
Social and Information Networks
CrossWeave: Bridging Perspectives Across Online Communities with a Dual-Pane Design
Fei Fang, Reva Hirave, William Jurayj et al. (+19 more)
Social media systems typically display conversations among already familiar contributors, which can be predictable and one-sided. In civic discourse, this design narrows discussion, reinforces divides, and distorts the perception of public opinion. To encourage cross-community engagement, we present CrossWeave, an AI-powered bridging system that augments the standard social media feed. As the user reads a post, CrossWeave surfaces diverse relevant posts from other threads in a side pane and highlights the connections. Users are invited to venture out of their echo chamber, explore a broader range of views and arguments, and “click across” to engage with their authors. When they do, CrossWeave facilitates constructive posting, not only by showcasing relevant past content but also by simulating possible reactions as the user drafts a post.
Read the full abstract ▾
All authors Fei Fang, Reva Hirave, William Jurayj, Yuqi Li, Brian Lu, Tarik Metin, Tsugunobu Miyake, Kateryna Morhun, Yash Permalla, Kenan Rustamov, Allen Shen, Haojun Shi, Prabhav Singh, Xiheng Tom Wang, Kevin Xu, Qingcheng Zeng, Jiayi Zhang, Daniel Khashabi, Andrew Perrin, Tiziano Piccardi, Ziang Xiao, Jason Eisner
Machine Learning
Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control
Yinan Huang, Shitij Govil, Bo Dai et al. (+1 more)
Many scientific
forecasting tasks require updating a distribution over future trajectories as new observations arrive. Conventional
diffusion and flow models generate each forecast from Gaussian noise, often at the cost of many sampling steps. Warm-start methods reuse earlier predictions to reduce this cost, but their models are not trained to perform the forecast update itself, which can compromise quality under few-step sampling. In this work, we introduce Seq-Flow, a conditional flow model whose ODE transports samples from the previous forecast distribution to the updated one. Because successive forecasts often differ only modestly, this transport starts from an informative distribution and can produce accurate updates with few flow evaluations. Recursive reuse also creates a challenge: errors in one forecast become errors in the initial states of subsequent flows. We address this with self-rollout training, in which a moving average copy of the model generates forecasts that initialize later training updates. Unlike self-forcing methods, which reuse generated outputs as conditioning context, Seq-Flow reuses them as the source of the next flow. Experiments On particle-accelerator beam spill
forecasting show Seq-Flow reduces CRPS by 65% under a few-NFE sampling budget, while remaining competitive with strong baselines on fluid-dynamics
forecasting tasks. Although trained on self-rollouts of at most four updates, Seq-Flow remains accurate over more than 400 consecutive updates. Our code is available at https://github.com/Graph-COM/Seq-Flow.
Read the full abstract ▾
All authors Yinan Huang, Shitij Govil, Bo Dai, Pan Li
Computer Vision
ECHO: Embodied Camera Observations of Human Object Carrying
Xuefei Sun, Lorin Achey, Kali Hamilton et al. (+4 more)
Embodied and assistive
agents must do more than recognize objects: they must reason about where an object belongs given the layout of an environment and the habits of the people who live in it. Progress on this problem has been limited, in part because no dedicated
benchmark or
dataset exists to define and evaluate it. Existing RGB-D scan
datasets reconstruct static rooms without human activity, while human-object-interaction
datasets capture motion without a navigable, fully reconstructed scene or a ground-truth notion of an object's natural destination. We introduce contextual object placement as a
benchmark task: predicting an object's destination during an observed object-carrying episode. To support this task, we present
Embodied Camera observations of Human Object carrying (ECHO), a large-scale synthetic
dataset that pairs dense RGB-D scans of indoor scenes with recordings of an
embodied human carrying everyday objects to context-appropriate destinations. ECHO is the first publicly available
dataset to combine reconstructed scenes, human activity, natural
language, and contextual-placement annotations. It comprises 3,805 human-annotated episodes across 159 floors of 115 HM3D scenes, involving 198 distinct objects. Each floor includes a complete RGB-D scan with human-annotated room labels and a surface list. Each episode provides synchronized RGB-D encounter clips; 6-DoF camera, human, and object trajectories; start and destination surfaces; an action caption; and a human-written context: a single sentence describing the inhabitant's routine that implies the destination without naming it. We evaluate contextual object placement using input-masked probes and an end-to-end baseline. Results show that no single input modality is sufficient, highlighting the need to jointly reason over scene structure, human activity, and contextual knowledge.
Read the full abstract ▾
All authors Xuefei Sun, Lorin Achey, Kali Hamilton, Alberto Speranzon, Gregory Grebe, Yonatan Bisk, Christoffer Heckman
Machine Learning
Q-Learning with Scalar Adjoint Matching
Yonghoon Dong, Minsung Yoon, Jaehyuk Kim et al. (+3 more)
Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a flow policy against a learned value function is not trivial, because the policy generates its action over many flow steps. Adjoint matching offers a principled way to update the flow model itself by propagating value information from the final action back to each flow step, but it requires a vector–Jacobian product through the policy at every step, a cost that grows with the number of flow steps and the policy size. We observe that the batch-averaged velocity Jacobian of pretrained flow policies concentrates on its diagonal. Motivated by this finding, we derive a closed-form scalar adjoint that scales the value gradient at the final action by the flow time, eliminating the per-step vector–Jacobian products. We further find that controlling the critic's value at policy-generated actions is particularly important under the scalar adjoint. Based on these findings, we propose Q-learning with Scalar Adjoint Matching (SQAM), which combines the scalar adjoint with a value penalty at those actions. SQAM's gains concentrate on the four hardest OGBench domains, where its success rate exceeds that of the strongest baseline in each domain by 18 to 35 percentage points. To test whether SQAM extends to large pretrained policies, we also fine-tune a
vision-
language-action policy on a real bimanual
robot. SQAM improves over supervised fine-tuning on all three tasks.
Read the full abstract ▾
All authors Yonghoon Dong, Minsung Yoon, Jaehyuk Kim, Jungwoo Park, Changyeon Kim, Jinwoo Shin
Computer Vision
Detecting Adversarial Images through Response Profiles of Vision-Language Models
Arash Vashagh and Roozbeh Razavi-Far
Adversarial perturbations can alter the predictions of frozen
vision-
language models (VLMs) while leaving their confidence and image–text similarity patterns seemingly plausible. We investigate whether we can identify
adversarial inputs based on the broader way an image interacts with a collection of general semantic
prompts. Our detector summarizes these responses using category-level statistics, relationships among
prompts, deviations from clean reference distributions, and stability under weak image transformations, producing a compact response profile that is classified by a lightweight model while the VLM remains fixed. We evaluate the approach on multiple public image
datasets, several CLIP-style visual backbones, and a range of gradient-based, optimization-based, automated, and spatial attacks. The detector achieves strong discrimination in attack-specific settings and retains substantial performance when evaluated on attacks not seen during training. Under a controlled detector-specific protocol, the response-profile representation outperforms the evaluated
embedding-geometry baselines. Additional analyses show that the feature groups provide complementary information and that the method remains effective under variations in the
prompt configuration. We also examine inference cost and performance against detector-aware adaptive attacks. Overall, the results indicate that response patterns across semantic
prompts provide a useful complementary signal for
adversarial image detection in frozen VLMs.
Read the full abstract ▾