Artificial Intelligence · Cross-listed from cs.LG
PokaiTrainer: Scaling Equilibrium Search to Competitive Pokémon VGC
Max Yu
Decision-time
equilibrium search carried poker to superhuman play, but it has so far relied on tractable subgames: a handful of actions per decision, chance confined to card deals, one player moving at a time. Competitive Pokémon in its official doubles format (VGC) breaks all three assumptions at once. Both players act simultaneously from joint menus in the hundreds, each joint action resolves to hundreds of
stochastic outcomes, and the opponent's reserves and stat allocations are hidden. No prior Pokémon
agent performs
equilibrium search, and whether it scales to this regime was open; we show that it does, and report what it took. PokaiEngine, our Rust battle engine, enumerates a joint action's full weighted outcome distribution in one pass, at ${\sim}99\%$ parity with Pokémon Showdown and a fraction of the cost of sampling it. PokaiTrainer adapts Student of Games to this scale and trains it by self-play over hundreds of human teams. Each decision is solved by counterfactual regret minimization as a
Bayesian matrix game over public belief states, subgames grow under an explicit compute budget, and value targets are harvested from the interior of every solve and grounded by realized outcomes. The strength is in the search. The network's policy alone loses even to a shallow heuristic search. PokaiTrainer is, to our knowledge, the first VGC
agent rated on the live Showdown ladder. Under open team sheets it wins 59% of 150 best-of-three sets against a human field averaging ${\sim}1320$ Elo, holds a 1350-1400 Elo band, and at its peak reached 1492 Elo, entering the format's top 500.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.NC
Rate-Coding Bundle Memory: A Unified Model of Memory and Control for Symbolic Computation in the Brain
Teun van Gils, Rowan P. Sommers, Markus Ostarek et al. (+1 more)
We propose a neurobiologically plausible model of cognition that combines the advantages of connectionist and symbolic systems, and that can explain a wide range of cognitive phenomena. This model, called Rate-Coding Bundle
Memory (RCBM), is based on the Symbolic Subsystem Hypothesis, which posits that the
brain implements a symbolic subsystem within its fundamentally connectionist nature. RCBM is a hybrid model that uses rate coding to represent symbols in a continuous space, and it uses a bundle
memory system to store and retrieve these symbols. The model is capable of solving a wide range of cognitive phenomena, including one-shot learning, pattern separation, and the binding problem. We argue that RCBM provides a promising framework for understanding the nature of cognition, and that it can be used to develop more sophisticated models of cognition in the future.
Read the full abstract ▾
All authors Teun van Gils, Rowan P. Sommers, Markus Ostarek, Peter Hagoort
Artificial Intelligence · Cross-listed from cs.LG
Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space
Qiancheng Zhou and Ruizhe Li
Reinforcement learning with verifiable rewards (RLVR) substantially improves single-sample accuracy (pass@1) but causes the policy's solution space to contract, diminishing the returns of test-time scaling. In this work, we investigate where inside a
reasoning trajectory this breadth is lost: does the policy fail to access a valid solution family, or does it fail to execute computation once initiated? To disentangle access from execution, we analyze the Countdown task, whose solution space can be exhaustively enumerated into discrete entrance families defined by the first operand and operator, across PPO on Qwen2.5-3B and GRPO on Qwen2.5-3B-Instruct. Across both training setups, solution coverage falls by up to 67%, halving even on problems solved across all checkpoints. We show that this contraction is heavily concentrated at the entrance: per-
token likelihood shifts are 11x–16x larger prior to the first arithmetic operation than during downstream
reasoning. Supplying only an unselected entrance prefix restores completion rates in low-access families by over an order of magnitude (0.018 -> 0.212 under PPO), demonstrating that alternative solutions remain executable but are no longer initiated. Guided by this localization, we find that while surface prompting fails to recover diversity, entrance-targeted interventions succeed: late-layer parameter interpolation with early checkpoints increases solution coverage by 37% at no loss in pass@1. Finally, we show that early-step
entropy collapse recurs across six math
benchmarks with 7B and 14B models, but is not an inevitable byproduct of
reasoning optimization: an SFT baseline preserves more than double the coverage, and staged SFT–DPO–RLVR pipelines retain early-step
entropy. In summary,
reasoning breadth is lost at the door, not inside the room. Code: https://github.com/ershiyidian/early-branch-locking.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
History-Conditioned Joint-Prefix Alignment for Generative Recommendation
Hongliang Sun, Lianjie Li, Bolin Zhang et al. (+3 more)
Generative recommendation retrieves items by autoregressively generating semantic identifiers, but beam search may discard a target before its complete identifier is generated. Our preliminary analysis across three
benchmarks shows that most missed targets are pruned within the first two decoding steps, highlighting the importance of early prefix retention. However, retaining a target's first-
token branch alone is insufficient if its continuation is pruned at the next step: aligning only the first-
token distribution improves first-
token survival but yields little gain in complete-path retention. This observation motivates joint supervision of early branches and their continuations. We propose Prefix
Alignment with Temporal History (PATH), which aggregates transition statistics from the training corpus over recent interactions with exponential decay to construct history-conditioned two-
token prefix targets. PATH aligns the model's joint predictions with these targets through forward KL divergence, using a chain-rule decomposition that enables unbiased Monte Carlo estimation. At inference time, PATH reuses the transition statistics for pointwise mutual information (PMI) calibration, reranking completed candidates relative to global prefix frequency. Experiments on Beauty, Instruments, and Yelp demonstrate the effectiveness of PATH, showing consistent improvements in recommendation performance and higher full-SID survival rates.
Read the full abstract ▾
All authors Hongliang Sun, Lianjie Li, Bolin Zhang, Dianbo Sui, Dianhui Chu, Zhiying Tu
Artificial Intelligence
An Explainable Coherence Score for Detecting Temporal Inconsistencies in Political News
Marius Nicusor Pantea and Adrian Groza
Temporal inconsistencies, such as mandates attributed outside their real interval, events presented as past before they occurred, or inverted causal sequences, are a form of political disinformation that evades style-based fake news detectors: a well-written article with a single wrong date carries no lexical signal of falsehood. This paper introduces the Temporal Coherence Score (TCS), a continuous, intrinsically interpretable metric that quantifies the temporal coherence of a news article, computed by a four-stage pipeline: extraction of temporal facts, construction of a temporal knowledge graph, hierarchical verification against internal consistency rules and external reference sources, and score aggregation with automatically generated explanations. Verification combines eight internal checkers derived from Allen's interval
algebra with a five-level external hierarchy ranging from a locally stored reference knowledge base of 1{,}256 curated political facts to live Wikidata SPARQL queries. On a
benchmark of 100 political news articles with injected temporal errors, the system reaches a precision of 0.909 at the selected operating threshold, with a single residual false positive, a profile deliberately tuned for human-in-the-loop fact-checking assistance, where false alarms are costlier than missed detections. Unlike lexical baselines that output only a binary label, every flagged article is accompanied by the inconsistency type, the entities involved, and the reference source that contradicts the claim.
Read the full abstract ▾
Artificial Intelligence
JudgePanel: A Compact Judge with Panel Deliberation via Adaptive Multi-Reward Reinforcement Learning
Yiyue Qian, Shinan Zhang, Huan Song et al. (+1 more)
The LLM-as-a-Judge paradigm has emerged as a scalable alternative to human evaluation. However, single-model judges are limited by their inherent model biases, while multi-
agent evaluation protocols that mitigate this through diverse deliberation are prohibitively expensive at inference time. To this end, we propose \modelname, which equips a compact \underline{Judge} model with multi-
agent \underline{Panel} deliberation capability. Specifically, we first train on panel deliberation traces from an ensemble of strong evaluators, capturing structured patterns of discussion, disagreement, and resolution. To further improve judgment quality beyond SFT, we introduce AdaReward, an adaptive multi-reward RL
algorithm that dynamically rebalances reward component weights as different objectives saturate at different rates during RL training. For practical deployment, we further design a lightweight domain specialization module for rapid adaptation to new evaluation domains with few hundred labeled samples. As a result, (i) Novel: the first framework to equip a single compact judge with multi-
agent panel deliberation capability at single-model inference cost; (ii) Effective & Reliable: JudgePanel with a 14B backbone outperforms judge-specialized models up to 70B across four evaluation
benchmarks, demonstrates strong position consistency, and rapidly specializes to new domains with few hundred samples.
Read the full abstract ▾
All authors Yiyue Qian, Shinan Zhang, Huan Song, Hannah Marlowe
Artificial Intelligence · Cross-listed from cs.CV
Subtraction-Based Tumor Segmentation and Lesion-Centered pCR Prediction for the MAMA-MIA Challenge
Kai Geissler and Raphael Schäfer
We describe the submission of team FME to the MAMA-MIA Challenge, which evaluated primary tumor
segmentation and prediction of pathological complete response (pCR) from pretreatment dynamic contrast-enhanced breast MRI on an external multi-country cohort. For
segmentation, we trained a five-fold residual-encoder nnU-Net ensemble using only the first post-contrast minus pre-contrast image, combined with mirroring test-time augmentation and largest-connected-component filtering. For pCR prediction, we ensembled 25 pretrained 3D
video classifiers trained on lesion-centred crops from the pre-contrast and first two post-contrast volumes. FME ranked second in both tasks. The
segmentation method achieved a combined performance-
fairness score of 0.882, with Dice 0.713 and normalized Hausdorff distance 0.099. The pCR method achieved a combined score of 0.664, balanced accuracy of 0.541, and equalized-odds disparity of 0.212. The results indicate that subtraction-based input and ensembling support robust tumor
segmentation under cross-site domain shift, whereas pCR prediction from baseline DCE-MRI alone remains limited. For the submission repository, see https://github.com/FraunhoferMEVIS/MAMA-MIA-Challenge-FME
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Training-Free Hidden-State Refinement for Flow-Matching Image Generators
Yuanyi Yan, Xinzhe Rao, Canyu Shen et al. (+5 more)
We aim to improve frozen flow-matching image generators by adding inference computation inside the denoiser, without changing model weights or the outer sampler. Existing generators usually spend extra test-time computation by increasing the number of sampling steps, which repeatedly evaluates the entire denoiser and couples quality gains to sampler cost. A key challenge is how to use extra computation inside a frozen
transformer denoiser: the method must decide which
tokens, layers, and sampling times receive repeated updates while preserving the original generation pipeline. We introduce a training-free looping framework that repeatedly applies selected
transformer layers inside each denoising call. Dense and Sparse
Token Loop vary the
token scope; Sampling-Progress Gating and the loop layer range specify when and where looping is active; loop count and strength control the repeated updates; and Loop Guidance combines ordinary and looped vector-field predictions. Across two Scale-RAE model scales, loop variants improve primary and auxiliary quality metrics with competitive quality–efficiency trade-offs. Loop Guidance further improves both primary metrics across all three tested models; on Scale-RAE DiT2.4B, it raises GenEval from 0.4471 to 0.5691 and DPG-Bench from 0.7656 to 0.8053. Code will be released.
Read the full abstract ▾
All authors Yuanyi Yan, Xinzhe Rao, Canyu Shen, Yang Chen, Yunlu Chen, Meng Tang, Teng Long, Vincent Tao Hu
Artificial Intelligence · Cross-listed from cs.CV
STARLINC: Satellite Trail Artifact Removal using Inter-Frame Correlation
Shingeon Kim, Hyeyoon Lee, Dain Kwon et al. (+5 more)
The rapid expansion of low Earth orbit satellites such as Starlink is increasingly contaminating astronomical surveys. In practice, contaminated images are often identified through inspection. However, modern surveys generate terabytes of data each night, making manual screening infeasible and necessitating reliable automated methods for satellite trail removal. Unfortunately, existing general-domain line detection methods fail to generalize to astronomical images due to domain mismatch, which are mostly grayscale with sparse bright
stars and have a low signal-to-noise ratio. Moreover, training new models from scratch is impractical due to the lack of large-scale annotated astronomical
datasets. To address these challenges, we introduce STARLINC, the first ML-based framework for satellite trail removal without requiring tedious pixel-level annotation of astronomical images. STARLINC combines synthetic satellite trail generation for training, inter-frame differential maps from temporally adjacent exposures to highlight transient trails, and heatmaps to provide additional localization cues for pixel-level
segmentation. Extensive experiments on real-world data demonstrate substantial improvements over baselines, establishing STARLINC as a scalable solution for next-generation astronomical surveys. Code is available at https://github.com/starioKim/STARLINC.
Read the full abstract ▾
All authors Shingeon Kim, Hyeyoon Lee, Dain Kwon, Kanghyun Choi, Sunjong Park, Mi-Ryang Kim, Jeong-Eun Lee, Jinho Lee
Artificial Intelligence
More Perspectives, Stronger Signals: Multi-Perspective Enhancement and Progressive Fusion for Multimodal Entity Representation Learning
Chenyi Xiong, Yan Zhang, Jing Hu et al. (+5 more)
Learning effective
multimodal entity representations is fundamental for
reasoning tasks such as
multimodal knowledge graph completion (MMKGC). However, existing methods often suffer from semantic over-smoothing within modalities and ineffective noise filtration across modalities, particularly under sparse or ambiguous conditions. To overcome these limitations, we propose PrismF, a unified framework that synergizes multi-perspective enhancement with progressive fusion to extract stronger signals from diverse inputs. PrismF enhances fine-grained intra-modal semantics through a multi-perspective mechanism that decomposes each modality into complementary views and constrains them with a decoupling loss to reduce representation collapse. Furthermore, it improves cross-modal integration through a progressive fusion strategy that dynamically calibrates inter-modal interactions, enabling the model to emphasize informative signals while suppressing noisy or unreliable ones. Extensive experiments on three public
benchmarks show that PrismF achieves the strongest overall performance, including relative improvements of 4.04% in MRR and 11.17% in Hits@1 on KVC16K. Our code can be found at https://github.com/HubuKG/PrismF.
Read the full abstract ▾
All authors Chenyi Xiong, Yan Zhang, Jing Hu, Ziyue Qin, Kui Xiao, Xiaopan Lyu, Xiaoju Hou, Zhifei Li
Artificial Intelligence · Cross-listed from cs.CR
Not the Same Protector: Deployment-Dependent Protective Intervention in LLMs
Eunna Lee, Soomyoung Lee, Jungpyo Nam et al. (+6 more)
We ask whether a model protects a user in the same way when that user speaks rather than types. Using a single distress vignette—a physical injury of unstated severity following an interpersonal conflict—we present four frontier models with matched inputs across voice, text, and raw API deployment conditions (n=30 per
cell) and code each response along five binary protective indicators, including whether the model issues an explicit medical-care directive. Voice-interface responses are markedly shorter than text-interface responses for three of the four models, and protective behavior contracts alongside that compression: medical directives are at ceiling under both the API and text conditions but decline under voice for every model tested. The contraction is not reducible to length. One model produces voice and text responses of comparable length yet still drops medical directives, and another falls below ceiling between its API and voice conditions, whose responses are of nearly identical length. Under raw API access the pattern is categorical rather than partial: no model asks after the user's safety even once. These results show that protective intervention is sensitive to the surface through which a request arrives, that this sensitivity is detectable using a simple protective coding scheme, and that it is not explained by turn length alone.
Read the full abstract ▾
All authors Eunna Lee, Soomyoung Lee, Jungpyo Nam, Heonjin Ha, Jamin Jung, Kyunam Choi, Sunjun Hwang, Yeonghun Kim, Seok-Jae Lim
Artificial Intelligence
APIFlow-Bench: Measuring Whether Agents Survive Long, Dependent API Workflows
Zelin Wan, Arash Nourian, Xiaoxiao Li et al. (+2 more)
Tool-using
agents are commonly evaluated by a single bit: whether an end-to-end workflow completed. This metric fails to distinguish failures that matter in production, such as expired credentials, malformed payloads, or correct execution followed by incorrect final delivery. We introduce APIFlow-Bench, a fully auditable
benchmark for long-horizon, dependent REST-API workflows that decomposes performance into seven engineering capabilities and requires
agents to produce answers supported by the actual call path. We generate synthetic API worlds forward, subtask by subtask; each subtask is admitted only after a zero-LLM self-test triad verifies its grader and an oracle establishes solvability, and an
adversarial audit identified and fixed six grader exploits. Grading is deterministic and provenance-sensitive: a state check traces a mock-minted canary through the API data flow to the response the answer must originate from, and a typed answer card is verified field by field. We release all answer keys and 44,362 unredacted execution transcripts. Across 19 frontier and open-weight models under one neutral scaffold, we find: (1) longer dependency chains degrade success, from 93% on individual subtasks to 74% on clean 20-subtask chains and 61% when including the 8% of chain trials that a model-consensus screen flags as passed by no model; (2) reliability separates models more than best-case capability, with best-of-five spanning seven points but all-five-of-five reliability spanning 44 points; (3) the independent-error account of compounding failure does not fit the data: pass rates on 20-subtask chains are 33 percentage points above the product of subtask-level rates, and on the clean slice 77% of failing runs reached the correct final state and failed only at delivery.
Read the full abstract ▾
All authors Zelin Wan, Arash Nourian, Xiaoxiao Li, Nihar Nandan, Kamalakannan Nandagopal
Artificial Intelligence
Beyond Correctness: Validity-Oriented Evaluation of Biomedical LLM Judges
Rodrigo de Oliveira, Federico Pittino, James Gwinnutt et al. (+1 more)
We propose a scalable, validity-oriented pipeline for evaluating biomedical LLM judges when high-quality human judgments are scarce. First, we augment existing human-labelled biomedical
benchmarks with deterministic, metric-grounded mutations that produce auditable preference pairs. Second, we evaluate judges beyond aggregate correctness using three deployment-relevant dimensions: correctness against metric-derived gold labels, robustness under repeated
stochastic sampling, and compliance with the requested output format. We use this pipeline to assess Llama-3.1-8B-Instruct under four regimes: (1) base, using the instruct model as is; (2) SFT,
distillation-based supervised fine-tuning only; (3) RL, GRPO-based reinforcement learning only; and (4) SFT$\rightarrow$RL, SFT followed by RL. The base and single-stage regimes struggle on structured medical discrimination such as PICO extraction and clinical calculations, whereas SFT$\rightarrow$RL performs best across correctness, compliance, and robustness; gains concentrate on decomposable tasks (PICO, MedCalc), at times matching or outperforming frontier models.
Read the full abstract ▾
All authors Rodrigo de Oliveira, Federico Pittino, James Gwinnutt, Jay Nanavati
Artificial Intelligence · Cross-listed from cs.CL
HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding
Dongwook Lee, Sangkwon Park, Eunwoo Song et al. (+6 more)
Speech Language Models (SLMs) are increasingly deployed in multi-speaker environments, yet their ability to attribute
speech to the correct speaker and reason over speaker identities remains unclear. Hence, we introduce HEAR, a conceptually hierarchical
benchmark diagnosing the foundational capabilities of speaker-attributed
reasoning, comprising 2.4K human-verified samples from 887 diverse multi-party audio clips. Evaluating 20 leading SLMs on HEAR reveals they struggle with these foundational tasks, often relying on semantic priors rather than actual vocal cues. To address this, we present A2R, a 30B model optimized on Counterfactual Audio with Speaker-level Hard negatives (CASH), a
dataset designed to guide the model to prioritize acoustic vocal cues over linguistic signals. A2R achieves strong performance on HEAR and exhibits zero-shot generalization to diverse multi-speaker downstream tasks, demonstrating that learned speaker attribution unlocks the model's latent capacity for speaker-aware
reasoning. All resources are available at https://attributetoreason.github.io/AttributeToReason/
Read the full abstract ▾
All authors Dongwook Lee, Sangkwon Park, Eunwoo Song, Che Hyun Lee, Youngho Cho, Junho Kim, June Young Yi, Heeseung Kim, Sungroh Yoon
Artificial Intelligence
Emergent Misalignment Is Not Magical
Mingxuan Li, Qirun Dai, Heran Wang et al. (+1 more)
Fine-tuning large
language models (LLMs) on narrowly harmful
datasets can lead to misalignment broadly, a phenomenon known as emergent misalignment (EM). EM poses a challenge for AI safety and our understanding of LLMs. Prior work often frames EM as an unexpected behavior, and explains it by appealing to general misalignment directions or anthropomorphizing it as acquiring an evil persona. However, the mechanisms behind these framings remain obscure. In this work, we show that EM is a predictable and data-dependent generalization phenomenon. By examining the base model's representation of EM training data and evaluation
prompts, we find that evilness after EM training is highly predictable from representational distance: the closer an evaluation
prompt is to training data centroid, the more evilness it elicits from EM models after training (with an average Spearman correlation of -0.73 across 12 model-
dataset settings). Building upon this analysis, we further demystify EM by showing that (1) its effectiveness changes significantly based on training data format; (2) there is not a general misalignment direction that transfers across different EM models; (3) the effect of EM is fundamentally different from persona changes. Furthermore, we extend the EM generalization metric from a scalar distance to a
dataset-specific generalization direction, which robustly predicts EM models' evilness under semantics-preserving
prompt perturbations including appending random
tokens and paraphrasing, where other methods do not reliably generalize.
Read the full abstract ▾
All authors Mingxuan Li, Qirun Dai, Heran Wang, Chenhao Tan
Artificial Intelligence · Cross-listed from cs.RO
Yuxiang Xiao, Xibei Chen, Xin Zhou et al. (+3 more)
Vision-and-
Language Navigation (VLN) requires
agents to reason over accumulated observations while continuously exploring unseen regions. However, existing environment representations often struggle to jointly support explicit semantic
memory and continuous exploration guidance. To address this challenge, we propose Cognitive Graph-Field
Memory (CGFM), a persistent
multimodal scene representation that couples explicit relational
memory with continuous spatial intuition. CGFM organizes objects, spatial relations, and visual observations into a
multimodal scene graph, enabling target
retrieval and long-horizon
reasoning across
navigation tasks. When no reliable target match is identified, graph-based evidence is projected into a goal-conditioned semantic-frontier field to guide exploration toward semantically promising frontiers and regions. Building upon CGFM, we introduce CGFM-Nav, a foundation-model-based framework for lifelong
multimodal navigation that integrates task-relevant subgraph selection, VLM
reasoning, and verification feedback into a closed decision loop. Preliminary experiments on GOAT-Bench show that, under the same Qwen3-VL-8B backbone, CGFM-Nav improves the overall success rate from 53.2% to 63.0% and SPL from 30.0% to 39.6%, demonstrating the effectiveness of combining explicit semantic
memory with semantic-guided exploration.
Read the full abstract ▾
All authors Yuxiang Xiao, Xibei Chen, Xin Zhou, Jie Chen, Yifeng Zhang, Guillaume Sartoretti
Artificial Intelligence · Cross-listed from cs.CR
Auditing and Mitigating Privacy Leakage in Cloud-Edge Collaborative Decoding
Kejia Zhang, Tianyuan Zou, Zixuan GU et al. (+1 more)
Applications such as personalized assistance and proprietary document analysis require large
language models (LLMs) to generate outputs from private data. Yet powerful LLMs typically cannot be deployed on the resource-constrained devices where private data resides, and uploading private data to cloud-hosted LLMs exposes sensitive information. Recent work addresses this tension with a cloud-edge collaborative decoding paradigm, where private data are kept on the edge with a small
language model (SLM) producing next-
token distributions, which are fused with predictions from a cloud LLM operating solely on public data. In this paper, we systematically analyze the
privacy risks of such a paradigm with a novel evaluation framework using constructed QA
datasets, which show that such collaboration can expose substantial private-context information. To address such
privacy leakage, we propose CoVeil, a defense mechanism which dynamically optimizes transmitted signals to suppress leakage during decoding time while preserving the collaborative quality. Extensive evaluations demonstrate that CoVeil consistently improves the
privacy-utility trade-off over existing baselines by reducing data leakage by up to 87.2%, with minimal accuracy loss.
Read the full abstract ▾
All authors Kejia Zhang, Tianyuan Zou, Zixuan GU, Yang Liu
Artificial Intelligence
Clustering as Approximation by Constrained Projectors: Theory and Guarantees
Angshul Majumdar
This paper develops a unified theoretical framework showing that a broad family of clustering methods, including k-means, fuzzy c-means, kernel k-means, kernel FCM, and spectral clustering, can all be expressed as structured low-rank projectors acting on a signal-derived
matrix. By formulating each method as an instance of min over B in C of ||M - M P_B||_F^2, with different constraint sets C, we establish a common optimization template that clarifies the algebraic links among hard, fuzzy, kernel-induced, and orthonormal projections. Within this framework, we derive non-trivial theoretical results, including geodesic convexity properties on the projection
manifold, perturbation bounds quantifying stability to
matrix noise, and exact recovery guarantees under ideal block-model conditions. The analysis further explains when different clustering families collapse to the same optimal subspace and how deviations arise under small inter-cluster leakage. Overall, the work provides a coherent, theory-first foundation for understanding clustering through structured projectors.
Read the full abstract ▾
Artificial Intelligence
SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models
Zongrui Wang, Xiangyang Zhu, Sicheng Wang et al. (+13 more)
Multimodal safety moderation requires distinguishing risks arising from visual content, user intent, and assistant behavior. Existing safeguards, however, are typically trained for a single judgment target and reduce safety assessment to a binary decision. Consequently, risk becomes difficult to compare across a
multimodal interaction, and ambiguous cases are obscured. We introduce SafeAtlas-VL, a
dataset of 1.5M training instances that places image-, request-, and response-level judgments on a five-level ordered scale. We curate a broad collection of safety-relevant data from both real-world and synthetic sources and apply a disagreement-aware annotation procedure. The resulting
dataset spans 15 harm categories and 55 fine-grained subcategories, covering a broad range of
multimodal safety scenarios. We also construct SafeAtlas-Bench, a held-out set of 5,000 instances for evaluating five-level predictions and continuous risk scores. Upon this
dataset, we train the SafeAtlas Guard series of models via target-conditioned tuning for
multimodal safety detection. Our models not only perform five-way classification of safety levels but also map safety to continuous scores through a soft cumulative ordinal head. Experimental results demonstrate that guard models trained on our
dataset exhibit strong generalization: even without using the training sets of other
benchmarks, they achieve competitive performance on the corresponding test sets. Notably, our 8B model attains the overall best performance, outperforming the previous SOTA by approximately 4% in F1 score. Code, data, and models are released to support further research. Warning: this paper contains example data that may be offensive, harmful, graphic, or disturbing.
Read the full abstract ▾
All authors Zongrui Wang, Xiangyang Zhu, Sicheng Wang, Han Wang, Dingyi Rong, Zeyu Zhang, Chunyi Li, Yue Shi, Kaiwei Zhang, Zicheng Zhang, Yuan Tian, Qi Jia, Yan Teng, Wei Sun, Ning Liu, Guangtao Zhai
Artificial Intelligence · Cross-listed from cs.LG
Development of an Autonomous AI Coding Agent using Monte Carlo Tree Search (MCTS) and Gemini LLM Frameworks
Pravin Game, Vipin Ramakrishnan and Prathamesh Wagh
The ongoing changes in software engineering requirements have created a substantial need for automated tools which can create secure source code from natural
language input. The performance of traditional Large
Language Models (LLMs) becomes limited by their "one-shot" capability which results in logical
hallucinations together with reduced algorithmic performance during complicated operations. The research presents an autonomous AI Coding
Agent which establishes a connection between LLM-generated content and production-ready software through its organized methodology for decision making. Our framework uses the Gemini 2.5 Flash API for essential
reasoning capabilities while employing a tailored Monte Carlo Tree Search (MCTS) method to solve code generation challenges as a search operation. The
agent uses a "Self-Critic" evaluator system to test different implementation methods which it ranks according to their accuracy and difficulty level before it improves its operational framework through backpropagation. The system operates through a Flask-based web interface which delivers instant feedback together with syntax highlighting features. Our experimental results show that the MCTS-based method achieves a 92% success rate on complex logical
prompts while surpassing standard zero-shot generation models.
Read the full abstract ▾
Artificial Intelligence
EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation
Sihang Jia, Shuliang Liu, Songbo Yang et al. (+1 more)
Large
vision-
language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is primarily incorporated into answer-side representations in early-to-middle decoder layers, while its direct influence progressively weakens in later layers. This attenuation suggests that visual evidence acquired earlier may be insufficiently utilized during subsequent generation. Based on this observation, we propose EviAnchor, a training-free and single-branch inference framework that preserves and reactivates visual evidence throughout generation. EviAnchor introduces Regional Evidence Anchor (REA) slots to progressively aggregate dense visual
tokens into spatially structured representations. It then strengthens the current decision state's access to these visual anchors through decision-conditioned evidence routing, mitigating excessive dependence on textual context. Finally, the model resumes its native
Transformer computation to integrate the retrieved visual evidence with question semantics and generation history. Experiments across POPE, CHAIR, and MMHal-Bench demonstrate consistent improvements in visual grounding.
Read the full abstract ▾
All authors Sihang Jia, Shuliang Liu, Songbo Yang, Xuming Hu
Artificial Intelligence
HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering
Zafar Ali, Asad Khan, Nimbeshaho Thierry et al. (+3 more)
Multimodal question answering remains sensitive to noisy, incomplete, and weakly grounded evidence. Long unstructured contexts can introduce redundancy and encourage unsupported generation, while flat
retrieval may overlook relations needed for multi-step
reasoning. We present HANIA, a planner-guided
multimodal graph framework for evidence-grounded question answering. HANIA processes the supplied image and text using a frozen
vision-
language model to extract concise question-relevant visual evidence with explicit abstention. It then constructs an input-grounded
multimodal graph and applies a two-group finite-state planner to coordinate descriptive and relational evidence. Coverage-aware
pruning retains a compact evidence set based on relevance, graph confidence, concept coverage, and modality diversity. The selected passages, visual statements, and graph triples are provided to a frozen instruction-tuned decoder. We evaluate HANIA on ScienceQA using answer accuracy, evidence-filtering quality, evidence-budget sensitivity, and efficiency. The results show that structured evidence planning and compact graph-guided
retrieval can support competitive
multimodal question answering without target-
dataset fine-tuning or iterative
retrieval. The code is available at https://github.com/Zafar-southeast/HANIA.
Read the full abstract ▾
All authors Zafar Ali, Asad Khan, Nimbeshaho Thierry, Nabila Amir, Adam A. Q. Mohammed, Pavlos Kefalas
Artificial Intelligence
Nested Convex-Body Chasing for Online Optimization with Evolving Feasible Sets
Dhruv Sarkar and Aprameyo Chakrabartty
We study online optimization with nested shrinking feasible regions in two settings: convex optimization with nested evolving feasible sets (CONES) and
adversarial constrained online convex optimization (COCO). Our
algorithms separate loss control from
geometric movement: constrained minimizers and cumulative-loss tests preserve regret guarantees, while a deterministic resettable nested convex-body chaser limits movement. For CONES with a $G$-Lipschitz, $\mu$-strongly convex objective on a diameter-$D$ domain, we chase intersections of the current feasible set with adaptive objective sublevel sets. Using the Euclidean chasing ratio $O(\sqrt{d\log(1+d)})$, we obtain nonpositive regret at every prefix and movement $O(\sqrt{d\log(1+d)\,GD\log(eT)/\mu})$. The bound adapts to the increase in the constrained optimum value. In dimension two, with all other parameters fixed, every randomized
algorithm with terminal expected regret $O(T^\beta)$, $\beta<1$, suffers $\Omega(\sqrt{\log T})$ expected movement on some deterministic nested sequence, proving optimal horizon dependence. Under linear growth away from the constrained minimizer set, Steiner-point tracking yields movement independent of $T$. For general convex COCO, one-step-delayed chasing with regularized-leader resets gives regret $O(G_fD\sqrt{d\log(1+d)T})$ and cumulative constraint violation $O(G_gD\sqrt{d\log(1+d)T})$. For strongly convex losses, both are $O(d\log(1+d)\log(eT))$ when other parameters are fixed. These reductions replace the $O(d^{d/2})$ projection-path factor in prior analyses by the
polynomial dimension dependence of Euclidean nested convex-body chasing.
Read the full abstract ▾
Artificial Intelligence
Revolutionizing Turn-by-Turn Navigation with Cloud-Edge Deep Learning
Yiming Yang, Hao Fu, Fanxiang Zeng et al. (+3 more)
Turn-by-turn (TBT)
navigation systems are integral to modern driving experiences, providing real-time audio instructions to guide drivers safely to destinations. However, existing audio instruction policy often relies on rule-based approaches that struggle to balance informational content with cognitive load, potentially leading to driver confusion or missed turns in complex environments. To overcome these difficulties, we first model the generation of
navigation instructions as a multi-task learning problem by decomposing the audio content into combinations of modular elements. Then, we propose a novel deep learning framework that leverages the powerful spatiotemporal information processing capabilities of
Transformers and the strong multi-task learning abilities of Mixture of Experts (MoE) to generate real-time, context-aware audio instructions for TBT driving
navigation. A cloud-edge collaborative architecture is implemented to handle the computational demands of the model, ensuring scalability and real-time performance for practical applications. Experimental results in the real world demonstrate that the proposed method significantly reduces the yaw rate (the proportion of vehicles deviating from
navigation routes) compared to traditional methods, delivering clearer and more effective audio instructions. This is the first large-scale application of deep learning in driving audio
navigation, marking a substantial advancement in intelligent transportation and driving assistance technologies.
Read the full abstract ▾
All authors Yiming Yang, Hao Fu, Fanxiang Zeng, Xikai Yang, Yue Liu, Ning Guo
Artificial Intelligence · Cross-listed from cs.CL
Not All or None: Dynamic Construction of Target-aware Memory Graph for Conversational Stance Detection
Yifan Xiang, Bin Liang, Yuqi Huang et al. (+2 more)
Stance detection is crucial for understanding the underlying attitude of an expression towards a target. Conversational stance detection is a more challenging stance detection task in real-world social media scenarios, as it involves detecting the user's stance by leveraging the target-related historical statements across conversational sessions. In this paper, we propose target-aware
Memory Graph TamGraph, a novel method that dynamically leverages target-related statements for conversational stance detection. Instead of considering all preceding historical conversations or using no prior conversation information for stance detection, our TamGraph employs a stepwise,
entropy-guided backtracking mechanism to selectively activate
memory from historical conversations and dynamically constructs a target-aware graph to model the stance relations among utterances. This allows the exploitation of target-related information from the conversation history for stance detection while preventing the introduction of noise. Experimental results on both English and Chinese
benchmarks demonstrate that our TamGraph substantially improves LLM performance on conversational stance detection.
Read the full abstract ▾
All authors Yifan Xiang, Bin Liang, Yuqi Huang, Ruifeng Xu, Kam-Fai Wong
Artificial Intelligence
Agent2UCB: Agentic System for Generative Engine Optimization
Sheldon Yu, Rui Wang, Tong Yu et al. (+4 more)
Large
language model driven search engines such as Google AI Overviews and Perplexity have created new opportunities for Generative Engine Optimization (GEO) the practice of refining content to increase its likelihood of being cited or summarized by generative systems. We demonstrate
Agent2UCB, an agentic GEO system that autonomously improves content visibility through customized, feedback-driven optimization. For each content item, the system evaluates nine GEO strategies, identifies the most effective method, and accelerates selection using a bandit-based
Agent2UCB policy that integrates LLM priors with online reward signals. To monitor side effects, the system also provides a lightweight, text-only SEO readiness evaluation covering readability, topical coverage, and EEAT-style credibility. Experiments on GEO-Bench show consistent visibility gains while preserving SEO quality. The demo allows users to choose the websites of interest, observe the optimization workflow, and compare GEO/SEO outcomes across methods.
Read the full abstract ▾
All authors Sheldon Yu, Rui Wang, Tong Yu, Sungchul Kim, Doga Dogan, Junda Wu, Julian McAuley
Artificial Intelligence
Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL
Shuomin Xue, Jingyuan Li, Ju Jia et al. (+2 more)
Graph Neural Networks (GNNs) have emerged as a cornerstone for representing complex relational dependencies in diverse multimedia tasks, particularly in cross-platform user interest modeling and cross-modal semantic
alignment. In the real world, a practical defense against graph
adversarial perturbations is needed. However, we observe that the prevailing
adversarial purification methods are essentially domain-restricted defenses, which leads to the following shortcomings: (1) single-domain data provides insufficient structural and semantic diversity for learning robust purification criteria; (2) training of domain-specific defense strategies from scratch consumes substantial computational cost. To address the above limitations, we propose a transferable graph purification scheme, named ProGAP, to bridge
adversarial defense knowledge via vulnerability-aware graph
prompt learning. Firstly, to capture universal
adversarial patterns, a perturbation-capture edge detector is pretrained on data-rich graphs by jointly modeling topological and semantic information. Subsequently, to achieve more knowledge transfer w.r.t. robustness, vulnerability-aware
prompts are designed that inject targeted purification guidance into biased nodes, during which the pretrained detector adapts to distribution shifts in downstream graphs without parameter-laborious updates. Experimental results demonstrate that compared with state-of-the-art baselines, our ProGAP achieves 1%-9% improvement, and reduces the time consumption by up to 2.2x. The code for ProGAP is available at https://github.com/Lieyoufffff/ProGAP.
Read the full abstract ▾
All authors Shuomin Xue, Jingyuan Li, Ju Jia, Jingxuan Yu, Xiaojun Jia
Artificial Intelligence · Cross-listed from cs.CV
DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering
Zihan Huang, Shihang Wu, Junle Liu et al. (+4 more)
Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the document question-answering capabilities of
Multimodal Large
Language Models (MLLMs). Applying restoration tools before Visual Question Answering (VQA) is an intuitive solution. However, existing restoration approaches remain limited, as manually designing and executing restoration strategies is labor-intensive and requires domain expertise. Agentic restoration offers new possibilities for automation, yet existing frameworks primarily target natural images and pursue perceptual quality, overlooking that restoration should serve downstream tasks rather than optimize generic image quality metrics. To this end, we explore the value of agentic restoration for real-world degraded document VQA and propose DocIntent, a training-free Answerability-Guided Agentic Restoration framework. DocIntent first assesses question answerability, then identifies task-relevant degradations and selectively invokes restoration tools. A Comparison-Based Rollback mechanism validates each restoration step and reverts it when question-relevant evidence becomes less decipherable. The entire process requires no additional pretrained degradation classifier or image quality assessment model. Extensive experiments on the WildDoc
benchmark show that DocIntent consistently improves the average score and consistency of different open- and closed-source MLLMs. The code and experimental data will be publicly available.
Read the full abstract ▾
All authors Zihan Huang, Shihang Wu, Junle Liu, Peirong Zhang, Yongxin Shi, Xuhan Zheng, Lianwen Jin
Artificial Intelligence
EmoLASP: Emotion Recognition with Language Models and Answer Set Programming
Thao Le and Michael Thielscher
Emotion recognition in conversations is increasingly tackled with
language models, but these models can be unstable and expensive to fine-tune or to
prompt with long dialogue histories. We propose EmoLASP, a framework that combines a
language model with declarative
reasoning via Answer Set Programming (ASP) to predict VAD scores (Valence-Arousal-Dominance) in conversations. Experiments on a widely used
benchmark dataset (IEMOCAP) across six open-source LLMs (3B-120B) and two PLMs (BERT, RoBERTa) show that EmoLASP improves prediction performance compared to using the
language model alone, even when the LLMs/PLMs are given no dialogue history in their
prompts or input vectors. The gains are largest for
prompt-only LLMs, which EmoLASP uses without any fine-tuning. However, for fine-tuned PLMs, the reasoner adds little once dialogue history is available. EmoLASP's LLM pipeline demonstrates the potential advantages of using a
reasoning approach to ensure
emotion prediction consistency and to reduce both the cost of fine-tuning and the cost of prompting with long dialogue histories.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability
Zhang Enyan and R. Thomas McCoy
A wide range of methods have been proposed for interpreting
language models, delivering important insights into their inner workings. However, different methods and their resulting insights stand in relative isolation: what could the underlying structure of
language models be, such that they give rise to all our interpretations? In this work, we propose using Tensor Product Representations (TPRs) as a unifying hypothesis. TPRs give a concrete proposal for how compositional structure could be represented in vector space — as filler-role bindings. We show, both mathematically and empirically, that TPRs can unify several prior interpretability methods: additive analogies, linear probing, sparse autoencoders, and activation patching. Mathematically, we show that these methods can all be derived from TPRs. Empirically, we apply the derivations to a range of different models — from small toy models to LLMs — to construct instances of each of the above interpretability methods; these constructed variants perform comparably to their standard variants. We view this work as a step toward what interpretability will ideally provide: a unified account of the nature of neural networks, corroborated not just by individual observations but also by an explanation of the connections between them.
Read the full abstract ▾