Game Theory
Anchored Sequential Deliberation
Sijing Tu and Ashish Goel
Sequential deliberation is a mechanism for collective decision making: at each round, a uniformly randomly selected pair is asked to revise a collective outcome, which then becomes the input for the next round. Existing theory by Fain et al.~\cite{fain2017sequential} treats the current outcome solely as the disagreement alternative in bargaining. Yet the existing outcome might also carry social influence and anchor participants' positions toward the status quo. In this paper, we introduce anchored sequential deliberation. At each round, two participants with bliss points $U$ and $V$ shift their positions toward the previous outcome $O_{t-1}$ with anchoring strength $0\leq \lambda<1$. They then bargain using $O_{t-1}$ as the disagreement alternative. For the sake of analysis, we assume that the decision space is one-dimensional, the anchoring effect is linear, and participants use Nash bargaining. The update simplifies to $O_t=(1-\lambda)Med\{U,V,O_{t-1}\}+\lambda O_{t-1}$. Our analysis reveals a trade-off. Through a coupling of two outcomes, we find that the process contracts in $1$-Wasserstein distance with a factor of at most $\frac{1+\lambda}{2}$, which implies that stronger anchoring slows mixing. On the other hand, stationary distortion weakly decreases with $\lambda$, although the worst-case distortion remains $\frac{1+\sqrt{2}}{2}$ for every feasible $\lambda$. We also identify a unique deliberative fixed point, at which the expected movement is zero, and prove that the stationary distribution concentrates around it as $\lambda$ increases. For symmetric populations, we further provide a tighter bound on the stationary variance around this fixed point. For the uniform distribution, we establish upper and lower bounds on stationary distortion, both of which approach $1$ as $\lambda$ increases.
Read the full abstract ▾
Computer Vision
Lesion-centered 3D mapping of colonoscopy procedures: validation of a hierarchical ensemble pipeline on public benchmark videos
Hyunjun Kim, Hyeonwoo Na and Jaewoo Lee
Background and Objective: Colonoscopy recording practice preserves text reports and still photographs, while the spatial information already present in the recorded
video - where the scope traveled, where a lesion was observed, and whether the same lesion was seen again - is discarded when the procedure ends. This study determines whether a lesion-centered spatial record can be assembled and validated without full-colon 3D reconstruction. Methods: A four-layer hierarchical pipeline was assembled - (1) a global topological map, (2) lesion-level spatio-temporal tracks, (3) on-demand local 3D reconstruction, and (4) persistent lesion identity across repeated observations - and ran end to end on four public
videos (two C3VDv2 sequences with ground-truth depth and two full REAL-Colon procedures; 40,245 frames). All components are published, individually validated methods; the contribution is their lesion-centered assembly, linking rules, and evaluation. Results: Revisits, impossible under forward-only mapping by construction, were detected by entry-map
Bayesian localization: 5,614 and 4,043 revisit events (56 and 68 distinct nodes) in the two full procedures. Lesion-identity merging at the adopted threshold 0.5 maintained ground-truth purity 1.0 while auto-merging 20 of 231 candidate pairs. The endoscopy-specific geometry engine outperformed a general-purpose foundation model on all metrics (overall absolute relative error (AbsRel) 0.2276 vs. 0.3523). Conclusions: The results are partial but establish a concrete near-term path: revisit detection, lesion identity, and local 3D each returned quantitative, reproducible output without waiting for complete
geometric reconstruction; validating the record on clinical data is the next step.
Read the full abstract ▾
Software Engineering
Memory-Skill Isomorphism: One Skill Carrier, Two Native Uses
Kang Ruiyuan
Memory and skills improve
agents without changing weights:
memory carries prior experience, skills carry reusable procedures. Wrapping both in stores, routers,
retrieval, reflection, and update paths makes reuse machinery grow with accumulation. Part of this duplication need not be rebuilt: a Skill is already a natural carrier for distilled
memory. Here the
memory component is a Skill: resident description holds hot cues, on-demand SKILL.md a colder index and curation policy, and reference/*.md files detailed
memories (levels L0 -> L1 -> L2). A governed 1,024-character description budget keeps the resident index compressed.
Memory and capability thus share one progressive-disclosure carrier; reflection evolves either Skill. Writes fork: history appended, current state rewritten and revalidated. In one deployed system, the sharpest identification is governance: 4 write entries exist, but only 1/4 reaches the settlement ledger. At the priced operating point, one L1 lesson-1 point adds 1,313 first-turn
tokens against a 1,462-
token baseline–tied at k=1 (1,313 versus 1,365), 4,949 at k=5; session totals differ by only 1.18x with overlapping last-turn ranges; price decomposition is unavailable. On one selected task with one model, exposing the lesson means fewer failures (0/8 or 1/8 with the lesson versus a shared non-concurrent 6/6 historical floor, unadjusted for multiplicity). The task was selected on prior floor evidence, so this is a selected-task post-selection existence signal, not a confirmatory rate. Resident and BM25 show no detected difference in two small comparisons. This motivates a candidate RSI design rule: one Skill carrier family, a shared read side, governed distinct writes. Body delivery h := P(D|A) is uninstrumented in RQ1–RQ2; this evaluates a resident-index implementation.
Read the full abstract ▾
Artificial Intelligence
ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds
Xiucheng Zhang, Zhuoning Xu, Hanjun Luo et al. (+3 more)
When a
language model plays a character, the observed behavior reflects both the assigned persona and the default dispositions of the actor model itself. Existing evaluations test persona fidelity or model defaults in isolation, but neither says, at a specific choice with consequences, what the persona changed and what the model's default kept. We introduce ANIMASK, a simulation framework that freezes books and scripts into story worlds whose characters act on their own motivations and replays each story from its freeze point. We hold out the author's continuation as a human reference, verify through in-story interviews that each persona remains present, and at every decision point compare the character's action with what the model produces when the persona is removed. Across 40 stories, 6 actor models, and 3,846 decision points, the replays converge away from their canons in one shared direction, toward flatter, cooler stories that leave their tensions open. The personas stay present and obeyed throughout. On three choices in four the model's default already falls inside what the persona accepts, and where the two diverge the model is the cautious one, holding where the persona would press. The persona guarantees who the character is, and the model sets how far the character will go.
Read the full abstract ▾
All authors Xiucheng Zhang, Zhuoning Xu, Hanjun Luo, Yankai Chen, Hanan Salam, Xue Liu
Systems and Control
Development of a 4D Cerebral Microvascular Imaging Platform for Mouse Stroke Model
Yoshihisa Kaneko, Moe Kumai, Hiroyuki Igarashi et al. (+5 more)
In ischemic stroke, changes in cerebral hemodynamics during both the ischemic and reperfusion phases strongly influence stroke outcomes. However, these hemodynamic changes remain incompletely understood. To address this challenge, we devised an imaging platform that enables time-resolved ultrasound microvascular imaging during the experimental induction of ischemia and reperfusion in a mouse model. The platform leverages our previous ultrasound imaging framework combined with continuous mechanical scanning, which acquires whole-
brain blood-flow signals within 5 s. The experiments demonstrated that the proposed platform can visualize both local and whole-
brain hemodynamic responses to the induction of ischemia and reperfusion, suggesting its potential for rapid and continuous whole-
brain hemodynamic assessment in small-animal models.
Read the full abstract ▾
All authors Yoshihisa Kaneko, Moe Kumai, Hiroyuki Igarashi, Daisuke Ando, Kuniyasu Niizuma, Hidenori Endo, Yoshifumi Saijo, Takuro Ishii
Machine Learning
Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers
Zhihao Guo, Zonghan Wu, Haizhou Du et al. (+4 more)
Looped
Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent
reasoning. However, additional iterations can reduce support for a reference answer, leaving unclear whether an update's direction is locally unhelpful or its full displacement moves too far. We study this distinction by analysing reference utility, which measures this support, along the model's own update direction, varying the fraction of the proposed displacement supplied to the readout. This reveals finite-step failures in which a locally improving direction produces a harmful full update. A pathwise
curvature decomposition characterises how initial progress is lost, while a local quadratic model predicts full-step gains and useful step scales. Bounds based on accumulated
curvature variation characterise the approximation error of these predictions. Experiments across two model families reveal this separation on mathematical and commonsense tasks. A fixed quarter step produces positive gains in reference utility for 72.2–83.2% of selected failures across four settings. These findings identify a mismatch between update direction and step scale as a mechanism of lost progress, explaining how some harmful updates retain useful computation.
Read the full abstract ▾
All authors Zhihao Guo, Zonghan Wu, Haizhou Du, Huan Huo, Yilei Shao, Athanasios V. Vasilakos, Qingsong Wen
Computer Vision
Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA
Yu Li, Zhengran Shen, Yachun Mi et al. (+2 more)
Leveraging Large
Vision-
Language Models like CLIP has recently set new
benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP inherently prioritizes semantic invariance, which often suppresses subtle perceptual signals, a phenomenon we term perceptual submergence. Furthermore, standard preprocessing techniques (e.g., cropping and interpolation) further exacerbate the loss of critical high-frequency quality cues. In this paper, we propose the Cross-modal Perception
Alignment Adapter (CMPA), a
manifold-aware framework designed to disentangle perceptual distortions from dominant semantics. CMPA introduces a Perception-Sensitive Feature Extractor (PFE) that projects CLIP features into a compact, low-dimensional subspace, explicitly magnifying distortion-induced off-
manifold deviations. Subsequently, a Cross-Modal Perception
Alignment Injector (PAI) aligns these features with quality-aware text anchors and re-injects them into the backbone. To ensure input fidelity, we also devise a Residual-enhanced Perceptual Downscaling strategy that adaptively compensates for resolution-induced information loss using Just Noticeable Difference (JND) guided frequency re-injection. Extensive evaluations on several
benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, effectively recovering the perceptual signals submerged in semantic-dense representations.
Read the full abstract ▾
All authors Yu Li, Zhengran Shen, Yachun Mi, Puchao Zhou, Shaohui Liu
Social and Information Networks
The Local-to-Global AD-k Conjecture is Resolved
Wei Chen
AD-k stands for Alternating Differences through order k, and it is a property of set functions denoting that the first order difference of the set function is nonnegative (a.k.a. monotnocity), the second order difference is nonpositive (submodularity), and so on with signs alternating through order k. Chen et al. [1] conjectured that in an influence
diffusion model called the general threshold model originally defined by Kempe et al. [2], if every local influence function is AD-k, then the global influence spread function is also AD-k, for any (possibly cyclic) directed graph and any k. This paper provides a complete proof showing that the
conjecture is true. The proof utilizes Möbius inversion, reverse reachable sets, and decision tree partition techniques and extends the probability distribution of node triggering sets into a generalized algebraic structure allowing negative weights for triggering sets. The extension to negative-weighted triggering sets may be of independent interest and may have further algorithmic implications.
Read the full abstract ▾
Computer Vision
SAVTrack: Selective Vote Aggregation for Reliability-Aware Point Cloud Tracking
Sifan Zhou, Linyue Tan, Qiwei Wang et al. (+2 more)
3D single object tracking (SOT) in
LiDAR point clouds is essential for autonomous systems, but remains challenging under sparse and incomplete observations. In such cases, different target points provide highly uneven constraints on the object center, causing some point-to-center votes to be substantially less reliable than others. Existing point-based trackers typically aggregate these hypotheses without explicitly modeling their reliability, allowing inaccurate votes to contaminate proposal clustering and degrade localization accuracy. To address this issue, we propose SAVTrack, a motion-aware tracking framework with Selective Vote Aggregation (SAV). SAVTrack estimates the reliability of each candidate vote from both local seed features and inter-frame motion context, and removes low-confidence hypotheses before proposal clustering. This pre-aggregation gating prevents unreliable hypotheses from affecting cluster formation while introducing only modest computational overhead. SAVTrack achieves competitive performance on KITTI and nuScenes, reaching 68.4/87.4 and 58.44/69.82 Success/Precision, respectively, while running at 82 FPS. It retains fewer than one-sixth of the candidate votes used by dense aggregation and remains particularly effective under sparse target observations.
Read the full abstract ▾
All authors Sifan Zhou, Linyue Tan, Qiwei Wang, Ziyu Zhao, Xiaobo Lu
Computation and Language
DiaWhisper-DPO: Role-Attributed Transcription of Clinical Interviews via Failure-Mined Preference Optimization
Weiming Li, Ana Catarina Fidalgo Barata, Miguel Constante et al. (+1 more)
Automated depression screening from clinical interviews requires attribution of utterances to the clinician or patient. We evaluate two
datasets: DAIC-WOZ, where participant-only recordings require re-synthesizing both sides for controlled two-party evaluation, and PDCH-HAMD, comprising voice-converted real Chinese interviews for cross-lingual validation. Cascaded systems combine speaker diarization with role-assignment heuristics, so errors can propagate across stages. We propose an end-to-end model, which we named DiaWhisper, that fine-tunes Whisper-large-v3 with LoRA and an auxiliary frame-level role head for transcription and attribution, together with DiaWhisper-DPO, a failure-mined refinement that uses genuine decoding failures as DPO rejected completions without human preference annotation. On 29 DAIC-WOZ test sessions, DiaWhisper-DPO achieves 0.973 role accuracy and 0.119 DER, 72% below the strongest cascaded baseline, and reduces seed variation from {\sigma} = .205 to .002. Retrained on PDCH-HAMD, it achieves 0.757 role accuracy and improves all 78 session-seed pairs.
Read the full abstract ▾
All authors Weiming Li, Ana Catarina Fidalgo Barata, Miguel Constante, João Miguel Sanches
Computation and Language
Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA
Kailong Fan, Anqi Pu, Yichen Wu et al. (+7 more)
Test-time reinforcement learning adapts a model on its own unlabeled test set using majority-vote pseudo-labels and has shown strong results in mathematics. We show that this recipe collapses on medical multiple-choice QA: accuracy stagnates while output diversity rapidly declines. Through a controlled experiment that keeps the questions, model, and optimizer fixed while changing only the answer space, we trace this failure to answer-space structure rather than domain difficulty. In small answer spaces, incorrect rollouts often collide on the same wrong pseudo-label and reinforce it; in large answer spaces, they disperse and receive little reward. This diagnosis motivates PROSE, Process Reward Guided Self-Training, which rewards
reasoning quality instead of answer agreement. PROSE scores each
reasoning step with a medical process reward model, assigns the trajectory reward as the minimum score across steps, and enforces answer-format constraints. Without labels, PROSE substantially improves a general Llama model, surpassing purpose-built medical models and matching much larger systems. Because the process signal is internalized into the policy, the adapted model requires no reward model at inference and transfers its gains to unseen
datasets. We further show that the minimum aggregation is essential: mean aggregation can be exploited, saturating the proxy reward while degrading accuracy.
Read the full abstract ▾
All authors Kailong Fan, Anqi Pu, Yichen Wu, Wanhua Li, Yicong Li, Hanspeter Pfister, Huafeng Liu, Xiang Li, Quanzheng Li, Ning Guo
Computer Vision
Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality
Jonghyeon Lim and Changhoon Yim
State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to
attention-based architectures and have been extended to
vision through ViM, VMamba, and Visual State Space Duality (VSSD). Yet the low-bit post-training quantization (PTQ) behavior of VSSD remains insufficiently understood. A weight-activation split on VSSD-Tiny identifies activation quantization as the dominant low-bit bottleneck, while representative inputs to selected VSSD-backbone linear layers exhibit strong channel-wise magnitude variation and
token-localized extremes. We propose the Channel-wise
Token-balanced Output-Aware Clipping (CTOAC) method, which learns per-input-channel clipping bounds by minimizing a
token-balanced reconstruction loss on the corresponding linear outputs. Only the selected linear layers and their input activations are quantized; other backbone operations retain their original precision. Across VSSD-Tiny, VSSD-Small, and VSSD-Base, the proposed CTOAC method retains ImageNet-1K accuracy and remains substantially more robust than the evaluated baselines at more aggressive precision settings. Applying the same quantization scope to VSSD backbones on COCO and ADE20K preserves strong object detection, instance
segmentation, and semantic
segmentation performance. An optimized RTX 4090 deployment configuration achieves up to 1.42x end-to-end speedup over FP32.
Read the full abstract ▾
Multimedia
Mechanism-Level Evaluation for Vision-Language Models: Controlled Activation-Replacement Diagnosis of Gender Bias
Zhipeng Zhao, Wenxu Wang, Peishun Liu et al. (+1 more)
Behavioral benchmarking reveals what biases exist in
vision-
language models but not which internal components are most sensitive to targeted intervention, precluding principled intervention. We argue for mechanism-level evaluation as a necessary complement, demonstrating causal mediation analysis as a diagnostic instrument for gender bias. We decompose gender-cue effects into controlled indirect effects attributable to specific-layer activations and direct effects through all other pathways, producing layer-by-layer mechanistic signatures. Across six models spanning three architectural families (LLaVA-1.5, LLaVA-NeXT, InstructBLIP at 7B/13B) and two 8B-scale architectures, three findings emerge:
language-layer activations exhibit the greatest output sensitivity under controlled intervention, with the direct component often carrying the opposite sign; architectural choices redistribute layer-wise sensitivity to activation replacement; and counterfactual scores diverge from surface-level scores, exposing implicit associations. Systematic ablation validates internal consistency. An intervention experiment finds that the average indirect effect (AIE) and downstream intervention effectiveness are only weakly correlated (Pearson $r = 0.33$), and the layer with the second-largest AIE produces near-zero bias change—indicating that mechanistic diagnosis captures activation-replacement sensitivity but does not, by itself, identify optimal intervention targets. These results show mechanism-level evaluation captures architecture-specific sensitivity patterns that behavioral
benchmarks cannot; pairing both should become standard NLP practice. Code: https://github.com/zhaozhipeng1997/CARD-GenderBias.
Read the full abstract ▾
All authors Zhipeng Zhao, Wenxu Wang, Peishun Liu, Ruichun Tang
Machine Learning
GrowMTP: Can RL Grow Its Own Draft Head?
Minghua He, Lingzhe Zhang, Yuan Liu et al. (+2 more)
Reinforcement learning (RL) post-training drives the frontier capabilities of large
language models, with its wall-clock dominated by autoregressive rollout generation. Speculative decoding is an established remedy for this bottleneck, but existing draft heads must be pretrained or warmed up before RL, introducing substantial training cost outside the RL run to be accelerated. We observe that RL training itself provides both conditions required for online draft-head training: its rollout distribution is far narrower than that of pretraining, and its verification step continuously produces supervision signals aligned with this distribution. Building on these observations, we propose GrowMTP, which uses this supervision to train a draft head from scratch entirely within the RL loop, with all head updates detached from the policy backbone. On Qwen3-4B (no draft head),
MiMo-7B-SFT (weak head), and Qwen3.5-4B-Base (strong head), GrowMTP achieves rollout speedups of 2.13x, 1.93x, and 1.36x, and end-to-end speedups of 1.60x, 1.41x, and 1.20x, respectively. GrowMTP therefore serves existing RL training frameworks as a modular component, particularly offering a from-scratch acceleration path for models without pretrained draft heads.
Read the full abstract ▾
All authors Minghua He, Lingzhe Zhang, Yuan Liu, Xiao Zhou, Aiwei Liu
Computer Vision
ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models
Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu et al. (+2 more)
Gender bias in large
vision-
language models (LVLMs) undermines their
fairness and reliability, compromising output trustworthiness. Current mitigation methods rely on training-phase adjustments or post-hoc calibration, but face limitations in dynamic visual bias mitigation. These include inability to capture real-time visual-textual incongruence, dependence on predefined gender bias taxonomies, and degraded cross-modal
alignment with emergent bias patterns. To address these challenges, we propose ViD, a causally-inspired framework that analyzes
attention mechanisms across five distinct patterns, revealing confounding effects from strong
language priors. ViD demonstrates that visual-to-
language cross-
attention effectively suppresses bias while preserving general
reasoning capabilities and text generation quality. ViD incorporates dual mechanisms:
backdoor adjustment counters strong
language priors, while refined
token selection in decoding layers optimizes processing. This enhances model robustness and inference efficiency. Our integrated approach significantly mitigates gender bias across multidimensional social attributes in LVLMs, improving visual grounding and output
fairness. Cross-
benchmark validation shows ViD reduces gender bias by 14.7% on single-attribute evaluations (FACET) and achieves significant improvements on image captioning tasks (MS COCO), with gender bias score improving from 0.6708 to 0.9978 for LLaVA. Crucially, these improvements require no additional training overhead, making ViD a scalable and practical solution for bias mitigation in LVLMs.
Read the full abstract ▾
All authors Zhipeng Zhao, Zhaoqiang Wei, Peishun Liu, Youwei Zhao, Ruichun Tang
Computer Vision
What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes
Zhipeng Zhao, Wenxu Wang, Peishun Liu et al. (+1 more)
When strong
multimodal models are widely available, progress requires new scientific methodologies beyond
benchmark scores—using models as instruments for understanding behavior. We address this by asking: can we use large
vision-
language models (LVLMs) as experimental instruments for studying their own failure dynamics? Focusing on visual
hallucination, we introduce SAFE, a training-free decoding framework that contrasts visually-grounded and
vision-ablated generation paths to produce a
token-level contrastive grounding score that identifies when the model favors linguistic priors over visual evidence. This signal serves dual roles: as a practical proxy for detecting visually-ungrounded
tokens, and as the basis for decoding-time penalties. Our analysis yields three empirical observations: visual dependency decays over generation,
hallucinations co-occur in temporal clusters, and early intervention reduces clustering without substantially degrading fluency. On MMHalBench, SAFE substantially outperforms all compared baselines; results elsewhere are more mixed. We argue that designing contrastive probes exemplifies a broader mission: using models as instruments for scientific understanding. Code: https://github.com/zhaozhipeng1997/SAFE_public.
Read the full abstract ▾
All authors Zhipeng Zhao, Wenxu Wang, Peishun Liu, Ruichun Tang
Human-Computer Interaction
Beyond Benefit or Risk: Perceived Impact Profiles of Human-AI Affective Interaction and Their Associations with Psychological Functioning
Lu Chen, Fenghua Tang, Jiayu Zhao et al. (+5 more)
Relational AI increasingly serves as an emotional shelter for humans, and its impact is mixed. Prior research has focused on either positive or negative impacts, leaving unclear how they are configured within individuals and relate to psychological functioning. To address these gaps, this study used a sequential mixed-methods design. Study 1 interviewed 52 users with emotional ties to AI and identified four positive impact domains (emotional relief, loneliness alleviation, enhanced interpersonal functioning, and personal growth) and four negative impact domains (virtual-real boundary blur, social replacement, cognitive-emotional reinforcement, and excessive use). Study 2 followed 673 Chinese AI users for six months and identified four profiles of individuals differently impacted by relational AI use: minimal impact, benefit-driven impact, mixed impact, and risk-driven impact. Users in the mixed impact and risk-driven impact profiles were both high in human-AI affective bonding, but those showing risk-driven impact had greater vulnerability, indicated by higher interpersonal need frustration and
emotion-regulation difficulties, more depressive and anxiety symptoms, and lower self-esteem and flourishing. Users in the benefit-driven and mixed impact profiles showed more favorable psychological functioning. After controlling for baseline functioning and relevant
covariates, Wave 1 profiles did not predict five of the six Wave 2 indicators; only users in the mixed impact profile reported higher flourishing than those in the minimal impact profile. Overall, potential psychological harms associated with relational AI engagement appeared limited and selective. These findings portray relational AI as a heterogeneous socio-emotional context that may partly mirror users' states and traits, warranting individualized, adaptive safeguards.
Read the full abstract ▾
All authors Lu Chen, Fenghua Tang, Jiayu Zhao, Xuanying Li, Yanli Wang, Weijia Fang, Mengyu Miranda Gao, Zhuo Rachel Han
Robotics
WholeBodyWAM: Generalizing Pre-trained World-Action Priors to Humanoid Loco-Manipulation via WBC-Grounded Coordination
Zhuo Li, Yiming Yao, Jim Tan et al. (+3 more)
World Action Models (WAMs) offer a promising approach to general-purpose
robot manipulation by jointly modeling visual dynamics and actions. However, most WAM studies focus on tabletop or arm-centric manipulation, while
humanoid loco-manipulation remains less explored. To address this gap, we introduce WholeBodyWAM, which jointly predicts future visual dynamics, manipulation actions, and whole-body control intents for generalizable
humanoid loco-manipulation. It preserves pre-trained world-action priors while grounding heterogeneous whole-body controller (WBC) semantics and coordinating whole-body behavior. Extensive experiments show that WholeBodyWAM achieves an overall simulation task success rate of 91.9%, with a 0.23 improvement in real-world out-of-distribution task progress and a 70% reduction in success-rate variance across WBCs relative to the respective baselines. These results suggest a path toward scalable
humanoid whole-body intelligence by extending pre-trained world-action priors through structured WBC grounding and coordination, rather than relearning whole-body behavior from scratch. Project page: https://wholebodywam.github.io/.
Read the full abstract ▾
All authors Zhuo Li, Yiming Yao, Jim Tan, Mengjie Jing, Zhipeng Dong, Fei Chen
Computers and Society · Cross-listed from q-fin.TR
From Public Evidence to Contractual Outcome: First and Stable Decidability on Kalshi
Maksym Nechepurenko
Public evidence can become sufficient to settle a prediction-
market contract before the venue records its first determination, but the relevant boundary depends on the applicable rule version, exact release object, source hierarchy, correction history, and unfinished contract conditions. This paper defines two Kalshi clocks: first decidability, the earliest contemporaneous singleton in the rule-evidence mapping, and stable decidability, the retrospective earliest time after which the same singleton remains unchanged through finalization. A completed retrospective identification test establishes a narrow feasibility result. In a frozen blind pilot, all 25 identities and blinding checks passed and current rule text was recovered for all 25; no exact or bounded historical rule version and no exact or bounded official source-release object was recovered. The full historical recovery covered 152,694 ordinary tickers, 11,530 exact event identities, and 6,540 read-only official requests, with zero historically eligible events and zero historically eligible tickers. This is an observability result, not a claim that no
market was decidable or that public evidence never existed. A completed prospective infrastructure shakedown established observation capability for three source programmes across 25
markets, with integrity revalidation of 781,266 lifecycle frames, 22 closed lower-bounded reconnect receipts, no unresolved reconnect gap, no due-but-missed official release, and an inactive price layer. Production evidence enrollment is active. The prospective sample is constructed only at enrollment close from prospectively frozen identities and pre-outcome fields; its frozen target size is selected mechanically under the registered full, reduced, exploratory, or no-go support disposition. No contractual-decidability clock, human-adjudication, price, or cross-venue result is reported here.
Read the full abstract ▾
Robotics
SAVLA: Symmetry-Aware Vision-Language-Action Models for Robotic Manipulation
Junle Li, Weixian Waylon Li, Fuxiang Wu et al. (+2 more)
Vision-
language-action (VLA) models have become the dominant paradigm for
language-conditioned
robot manipulation. However, although images and
language instructions inherently encode
geometric information, VLAs acquire their spatial competence purely from demonstrations. As a result, they are reliable only within the range of scene poses that the demonstrations cover. We propose SAVLA, an end-to-end
symmetry-aware VLA model for robust and data-efficient policy learning. Our approach keeps the pretrained
vision-
language backbone entirely frozen while combining it with an equivariant flow-matching action head and a learned canonicalizer. The head decomposes its state, action, and conditioning inputs into invariant and equivariant channels, and preserves this typing throughout all of its layers. The canonicalizer transforms oblique-view images into a canonical frame and rotates the
geometric conditions consistently. We evaluate our model on LIBERO. Compared with the GR00T N1.5 baseline, SAVLA improves the success rate averaged over all four LIBERO suites by 5.1 points and increases the mean success rate under rotation on LIBERO-Goal from 41.5% to 90.4%.
Read the full abstract ▾
All authors Junle Li, Weixian Waylon Li, Fuxiang Wu, Fusheng Hao, Fengxiang He
Artificial Intelligence
ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training
Zhihao Zhang, Mingqi Wu, Qiaole Dong et al. (+15 more)
Continual post-training of large
multimodal models should add new capabilities while preserving those from pre-training, and the two goals pull in opposite directions. SFT gives explicit target supervision that learns a task from near-zero accuracy, but its off-policy targets move the model far enough to cause forgetting; on-policy methods such as RLVR and self-
distillation preserve policy proximity yet supply little signal when the policy cannot yet solve the task. We introduce ReDraft (Reference-Driven Revision and Fine-Tuning), which obtains both from the model's own failures: using an expert response only as a reference, it has the model revise its own incorrect rollout, keeps the revision only if a verifier accepts it, and fine-tunes on what survives. Each retained target is therefore explicit, yet still close to the current policy. Across Counting, Clock Reading, and Jigsaw on Qwen2.5-VL-3B/7B, two of them with near-zero accuracy, ReDraft gains 56.9 points on the target task against SFT's 52.9 while cutting prior-task loss from 16.6 to 1.5 points (11.3x less forgetting), and improves on OPSD along both axes (19.3 gain, 6.2 loss). Data- and parameter-space analyses match the design: revised targets are more probable under the base model, and the updates they induce stay compact and follow SFT's direction more closely than OPSD's. Together, these results show that revising the model's own rollout rather than directly imitating an expert trajectory can reconcile cold-start acquisition with prior-capability retention.
Read the full abstract ▾
All authors Zhihao Zhang, Mingqi Wu, Qiaole Dong, Enyu Zhou, Shuo Li, Boyang Liu, Jiazheng Zhang, Honglin Guo, Xin Guo, Shaofan Liu, Junzhe Wang, Dingwei Zhu, Minlong Peng, Yuan Hua, Zhiheng Xi, Qi Zhang, Tao Gui, Xuanjing Huang
Computer Vision
Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision
Yanick C. Tchenko, Felix Mohr, Hicham Hadj-Abdelkader et al. (+1 more)
Efficient perception is central to robotic systems operating under constrained computation,
memory, and latency budgets. Knowledge transfer from larger pretrained models offers a practical route to stronger compact perception networks, but existing approaches commonly rely on fixed
distillation objectives or manually designed interaction mechanisms. Building on Hereditary Knowledge Transfer (HKT), we propose LePoKet (Learnable Parameter Optimization for Knowledge Transfer), a structural transfer framework that embeds knowledge inheritance directly into the forward computation. LePoKet introduces a block-wise Extract-Transform-Mix interface whose interaction parameters are optimized jointly with the child network through a Learnable Genetic
Attention (LGA) operator, without auxiliary
distillation losses or temperature scaling. We first characterize the mechanism on CIFAR-10 and CIFAR-100 using ResNet parent-child pairs, obtaining relative error reductions of 24.57% and 25.1%, respectively, over standard child training. We then evaluate LePoKet for dense motion estimation by integrating it into a compact RAFT-based optical-flow model trained only on FlyingChairs and FlyingThings3D. LePoKet improves the compact RAFT baseline from 2.21 to 1.92 EPE on Sintel Clean, from 3.35 to 3.01 on Sintel Final, and from 7.51 to 6.39 on KITTI. A direct comparison with HKT further shows that LePoKet improves CIFAR-10 accuracy from 92.40% to 93.40% while achieving the best Sintel Final and KITTI errors among the evaluated compact transfer variants, with comparable performance on Sintel Clean. These results demonstrate that learnable structural transfer generalizes across recognition and motion perception tasks and provides a promising approach for efficient robotic
vision.
Read the full abstract ▾
All authors Yanick C. Tchenko, Felix Mohr, Hicham Hadj-Abdelkader, Hedi Tabia
Artificial Intelligence
EchoPath: Execution-Level Replayable Memory for GUI Agents
Yao Zhao, Aditya Shanmugham, Swastik Roy et al. (+1 more)
Computer-use
agents increasingly operate browsers, software, and desktop applications via CLI or API portals, but graphical user interface (GUI) still plays an important role in common industrial production scenarios. GUI
agents commonly employ fresh observe-plan-ground-act loops, which is inefficient for enterprise tasks that repeatedly update records, process forms, configure tools, and export reports. We introduce EchoPath, a model-agnostic harness that converts artifact-validated GUI trajectories into standardized, parameter-controlled callable
memories, analogous to Model Context Protocol (MCP)-style tool calls rather than unstructured experience records. Each
memory stores task-intent keys, application and state preconditions, flexible input parameters, GUI evidence, validation provenance, and lifecycle state, so the host
agent invokes a targeted procedure only when it can be deterministically replayed in the current runtime. The core mechanism enabling replay is an image-based target-reaiming
algorithm that treats stored coordinates as visual evidence, matches the remembered GUI target against the current screen, and emits corrected operation coordinates before execution. During replay, EchoPath rebinds only declared modifiable inputs and rejects ambiguous or incompatible steps to bounded grounding repair or fresh planning. In experiments with real computer-use tasks, EchoPath reduced median
token cost by more than 90% and median execution time by about 60%. These results support a bounded form of enterprise GUI
memory: validated execution experience can become a controllable callable asset for recurrent work rather than only context for another
reasoning pass.
Read the full abstract ▾
All authors Yao Zhao, Aditya Shanmugham, Swastik Roy, Yanxun Xu
Social and Information Networks
Inferring Temporal Dependencies from Social Time Series with the Cross-Correlogram
Bridget Smart, Renaud Lambiotte, Takaaki Aoki et al. (+1 more)
Characterizing temporal interactions in social systems is challenging because social behavior can be bursty and non-stationary, violating the stationarity assumptions of many methods used to measure temporal dependence. The cross-correlogram, an existing technique used to profile neural excitations and inhibitions, offers an interpretable alternative to methods such as Granger causality or co-occurrence, as it produces a full profile of lagged dependence directly from event times rather than a single summary statistic. We adapt the cross-correlogram by integrating functional models of behavior with data-driven temporal response profiling. By characterizing how periodic structure biases traditional cross-correlograms, we propose a correction based on smooth intensity functions, specified from a known functional form or estimated empirically. This approach provides a robust, interpretable
estimator of temporal dependency profiles even when collective rhythms operate on timescales that overlap those of the interactions of interest. We demonstrate theoretically and through simulation that the proposed method recovers temporal dependencies in periodic regimes, outperforming interval-jitter and Granger causality methods. Finally, we apply the method to 3.1 million event times from X (formerly Twitter) collected between 2019 and 2020, demonstrating how cross-correlograms reveal delayed temporal relationships in collective online behavior that are missed by co-occurrence measures. For a subset of television-related hashtags, recovered delays align with known broadcast schedules, providing evidence that the proposed method captures genuine temporal structure rather than artifacts of shared
attention cycles.
Read the full abstract ▾
All authors Bridget Smart, Renaud Lambiotte, Takaaki Aoki, Ryota Kobayashi
Robotics
Learning to Optimize UAV Path Planning for Data Sensing in Wireless Sensor Networks
Sijie Ma, Zeyuan Ma, Weijia Cao et al. (+4 more)
UAVs have emerged as highly flexible platforms for data sensing in Wireless Sensor Networks (WSNs). Path planning for
UAVs in such tasks plays a key role to assure remote sensing effectiveness and friendly energy consumption. However, existing approaches show two key limitations: i) they are primarily hand-crafted with certain design biases that harm adaptation on unseen tasks. ii) they predominantly assume idealized spatial complexities of actual environments through simplified simulation, causing them to underperform during real-world deployment. In this paper, we propose a novel learning-assisted planning framework, termed Landscape-Aware Meta Differential
Evolution (LAMDE), to tackle the mentioned limitations. The major contributions come from the following aspects. We first re-formulate such
UAV path planning problem to embrace challenging constraints. To efficiently navigate this highly constrained space, we propose a bi-level learning to optimize approach, where the meta-level is a trainable
algorithm configuration policy that meta-learns an adaptable planning strategy for low-level planning
algorithm. To address the potential training data scarcity and distribution shift in real-world environments, we introduce a landscape-aware automatic augmentation scheme that enriches training data. At the low-level, a Differential
Evolution algorithm is deployed for solving the path planning tasks. To enhance the solving flexibility, we further design a variable-length encoding strategy that dynamically prunes redundant hover points and optimizes continuous flight parameters concurrently within a unified search space. Based on all proposed designs, we meta-train LAMDE and compare it with representative baselines. Comprehensive experiments demonstrate that LAMDE achieves state-of-the-art performance on the tested complex
UAV path planning tasks in WSN data collection scenarios.
Read the full abstract ▾
All authors Sijie Ma, Zeyuan Ma, Weijia Cao, Yue-Jiao Gong, Lingling Ma, Zhiyang Huang, Jun Zhang
Computation and Language
Quantifying Organizational Environmental Action from Web Data and Large Language Models
Quinn Reynolds, Daniel Shore, Vianey Leos Barajas et al. (+2 more)
Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because relevant information can be dispersed across multiple webpages and is primarily communicated through unstructured text. We present a scalable computational framework for transforming organizational web content into structured measures of environmental action and demonstrate the approach using Jewish congregations in the United States. We constructed a national database of 4,964 congregations by integrating multiple geospatial, knowledge-base, directory, and manually reviewed sources. Of these, 2,657 had active websites that were successfully crawled, producing a corpus of 154,454 webpages. We compared three approaches for detecting environmental actions: keyword
retrieval followed by large
language model (LLM) classification, semantic vector
retrieval followed by LLM classification, and direct LLM classification classification without preliminary
retrieval. Agreement with an expert human reviewer was lowest for keyword
retrieval ($\kappa$ = 0.26), higher for semantic vector
retrieval ($\kappa$ = 0.42), and similar for direct LLM classification ($\kappa$ = 0.40). Although semantic
retrieval achieved the highest agreement, its
retrieval recall was 0.87, indicating loss of relevant content before classification. Applied to the complete corpus, direct LLM classification identified at least one environmental action at 1,398 congregations (53%), providing greater coverage than either
retrieval-based approach. These results demonstrate that preliminary
retrieval can reduce computational cost but may exclude relevant information before it reaches the classifier. The framework provides a reproducible approach for extracting organization-level environmental information from unstructured web content that can be adapted to other institutions.
Read the full abstract ▾
All authors Quinn Reynolds, Daniel Shore, Vianey Leos Barajas, Tanhum Yoreh, Meredith Franklin
Computer Vision
JewelTry: Mask-Free Scale Aware Jewelry Virtual Try-On
Xinlei Niu, Peixia Li, Jun Wang et al. (+5 more)
Virtual try-on (VTON) enables customers to visualize how fashion products appear when worn and has become an important technology for online shopping. While recent advances have substantially improved garment VTON, jewelry remains a challenging and underexplored category due to its small size, rigid structure, and sensitivity to fine-grained visual details. Realistic jewelry VTON requires not only faithful appearance transfer but also accurate scale and placement relative to the wearer. Existing jewelry VTON methods typically rely on mask guidance, whereas mask-free approaches lack explicit guidance for modeling the product scale. To bridge this gap, we introduce JVTO-Bench, a
benchmark dataset for scale-faithful jewelry VTON, providing reference source target triplets with real-world product-scale annotations across four major jewelry categories. Building upon this
benchmark, we propose JewelTry, a mask-free
diffusion framework for scale-aware jewelry VTON. JewelTry incorporates a scale adapter that encodes product dimensions into a scale
token, enabling the model to learn scale relationships between jewelry items and surrounding human anatomy in-context. To further improve jewelry consistency, we introduce a single-directional condition
attention mechanism and an
attention refinement loss that preserve both coarse geometry and fine-grained structural details of the reference jewelry. Extensive experiments show that JewelTry achieves a balance among visual fidelity, background preservation, object consistency and scale accuracy, establishing a strong baseline for mask-free, scale-aware jewelry virtual try-on.
Read the full abstract ▾
All authors Xinlei Niu, Peixia Li, Jun Wang, Chenchen Xu, Jiayu Yang, Jing Zhang, Pulak Purkait, Hongdong Li
Information Retrieval
AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale
SungGeun Kim, Abhinav Narain and Daniel Nemirovsky
How and why does a recommender system fail the users it serves? Oftentimes, practitioners are left to improve their
algorithms based on a combination of feedback from stakeholder teams, domain expertise, and insights from data analyses. Yet the nuances of how and where recommendations perform well or poorly for end users are difficult to discern from aggregate quantitative metrics. Whereas these metrics provide a high-level and incomplete picture, further granularity into the quality of recommendations and their patterns requires
reasoning with domain understanding and objectivity, at scale. We contemplate this complex conundrum and describe a method and implementation that uses the latest AI agentic advances to provide actionable diagnoses and improvements for production recommender systems. We present AURA (Agentic Understanding and Refinement of recommender
Algorithms), an end-to-end agentic system that performs qualitative evaluation at scale and can then generate improvements to our
algorithms at the code level. Specialized
agents read production engagement logs, from thousands of sessions to millions, and surface patterns and examples of how the recommender fails real users. The next step uses those diagnoses and context about the recommender's own code, data, and training pipeline to propose and implement refinements grounded in that codebase. We report the system design, initial tests on production data from two large consumer platforms at a major media-streaming company, safeguards, operational learnings, and early results toward a self-improving recommender system. Finally, the diagnostic gap AURA closes is not specific to streaming. The architecture is built to transfer: every domain-specific element enters through the configuration layer that already ported it between our two platforms. We map it concretely to e-commerce and online-retail recommendation.
Read the full abstract ▾
Machine Learning
Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction
Junyi Liao, Johann Guilleminot and Vahid Tarokh
Neural PDE solvers provide efficient surrogates for time-dependent physical systems, but autoregressive prediction over long horizons remains challenging because local errors can induce distribution shift and accumulate under recursive deployment. We develop a variational approach to this problem by introducing latent Markov dynamics in which physical states are represented by latent distributions and evolved through probabilistic transitions. The framework is formulated directly on function spaces and specialized to functional Gaussian models, where structured latent perturbations induce a spectral geometry and variational transition
alignment regularizes the learned dynamics. We further analyze how these mechanisms affect autoregressive error propagation, providing a theoretical connection between variational training and long-horizon prediction. We instantiate the framework as the Variational Autoencoding Markov Operator (VAMO), which combines spatially resolved latent fields, structured Gaussian perturbations, and a neural-operator transition. Empirically, we demonstrate the effectiveness of VAMO on several fluid-dynamics
benchmarks with prediction horizons extending substantially beyond those represented during training, where it consistently reduces error accumulation and improves rollout stability over several deterministic and noise-injection baselines. Overall, these results highlight variational modeling as a complementary approach to robust long-horizon neural PDE dynamics.
Read the full abstract ▾
Machine Learning
Divergence Timing and Cumulative Disagreement under KV-Cache Eviction
Xinyue Luo and Fei Yu
KV-cache eviction perturbs the conditional
token distributions governing autoregressive generation. We investigate how first-divergence timing and subsequent
token mismatch determine cumulative disagreement. We derive an exact decomposition under a specified stepwise maximal coupling: the expected mismatch fraction equals a first-mismatch contribution plus post-divergence exposure multiplied by its mismatch rate. An explicit construction over unrestricted autoregressive kernel pairs realizes the sharp interval of risks compatible with a finite divergence-aligned observation window. Residual-branch conditional Monte Carlo provides unbiased joint estimates of occurrence, occupation, and window/tail contributions, with per-replicate variance dominance for total
token loss. Complete trajectories from Meta-Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct show that SnapKV at 50% retention enters divergence later and less often than SnapKV-512 or recent-
token retention with the same 50%
prompt-cache budget, while post-divergence total variation (TV) remains high. In an exploratory analysis of 288 documents, post-divergence exposure accounts for 85-90% of four aggregate mismatch gaps. On 288 independent documents at 90% retention, prespecified comparisons show higher branch-aligned TV in the late than in the early window in both models.
Read the full abstract ▾