Artificial Intelligence · Cross-listed from q-bio.QM
STAMP as a topology-aware molecular language for fragment-level learning and editing
Yuxuan Ren, Jiatong Li, Ziqiao Meng et al. (+1 more)
Molecular fragments provide chemically meaningful units, but existing molecular
languages rarely make their locations and connections explicit for editing. Here we introduce STAMP (Sequential Tree Attachment-based Motif-Preserving representation), a
topology-aware molecular
language that connects fragment-level representation learning with precise structural editing. STAMP separately encodes motif identity, attachment sites and tree
topology, making fragments reusable across contexts and subtrees directly accessible. Learned representations capture motif similarity and recurring transformations, and lower activity-cliff prediction error on 23 of 30 targets versus a matched SMILES encoder. Compatible subtree operations support scaffold-preserving optimization, ranking first among six methods on 15 of 23
benchmark objectives. A deterministic compiler enables frozen
language models to act on indexed fragments, improving molecular editing, optimization, transformation transfer and change identification by 9 to 56 percentage points over plain SMILES. Together, these results establish an executable molecular
language in which learned chemical units remain directly operable during design.
Read the full abstract ▾
All authors Yuxuan Ren, Jiatong Li, Ziqiao Meng, Yatao Bian
Artificial Intelligence · Cross-listed from q-fin.GN
How Well Do LLMs Perform in Peer Review? Evidence from Finance and Accounting
Hai Lu, Yichen Luo and Luping Yu
Referees increasingly use large
language models (LLMs), while finance and accounting journals disagree about whether to allow it. We ask which part of a referee's job the models can do. GPT-4o, whose training data end before the 2024 conference season, referees the papers presented at the 2024 AFA and NBER finance meetings, and we compare its verdicts with publication in the top-three finance journals over the next two years. Papers the model scores one standard deviation higher are 44% more likely to be published, net of author reputation. The result is not driven by look-ahead bias, as the model does not recall the outcomes. The information comes from its judgements of correctness and exposition. Its judgements of originality and significance carry none, and a referee guide that stresses importance does not help. The split between correctness and contribution holds for accounting papers and for a newer model, GPT-5. LLMs can check whether research is right, but not whether it matters. The technical check can go to the model, while the judgement of contribution stays with people.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation
Xi Chen, Chunyi Zhou, Rui Zeng et al. (+3 more)
Federated fine-tuning of large
language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering strong
privacy benefits. However, this setting is highly vulnerable to backdoor attacks, in which malicious clients manipulate their updates to induce targeted behaviors while maintaining normal performance on benign inputs. In this work, we make a key observation specific to
federated LLM fine-tuning: malicious clients tend to exhibit strong consistency in their model updates, whereas benign clients produce more diverse and dispersed updates. This structural difference is not well captured by existing defense methods, which typically rely on direct anomaly detection in high-dimensional parameter space and therefore struggle in the presence of entangled LLM updates. Motivated by this observation, we propose FedGraph, a graph-based aggregation framework that explicitly models relationships among client updates. By representing clients as nodes in a dynamically constructed graph and extracting structural features that characterize their relative positions and interactions, FedGraph derives compact client representations that effectively separate malicious and benign behaviors. These representations are then used to identify and suppress malicious contributions during aggregation. Extensive experiments demonstrate that FedGraph significantly improves backdoor defense. It consistently reduces attack success rates to below 10% while achieving high detection accuracy (95.5% on average) and a low false positive rate (2.33%), substantially outperforming existing
federated learning defenses.
Read the full abstract ▾
All authors Xi Chen, Chunyi Zhou, Rui Zeng, Xiaogang Xu, Zhe Liu, Shouling Ji
Artificial Intelligence · Cross-listed from cs.CL
Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages
Ramchand Kumaresan, Madhusudhanan G and Kaushik Kezendirane
We trained Agaram 2.5B, a 2.5-billion-parameter Tamil-English
language model, from scratch on about 50 billion
tokens (58% Tamil, the rest English, math, code and parallel text) on one node of eight H100 GPUs in about six days, with a new tokenizer that, unlike our first model's, keeps line breaks. Supervised fine-tuning on 134,428 conversations, whose replies an open-weight teacher model wrote, and three short targeted rounds turned it into a chat model that answers in Tamil script, romanized Tamil (Tanglish) and English and can call tools: on 25 tool
prompts whose schemas appear in training it picks the right tool 23 times and gives exactly the expected arguments 13 times. The released model translates better than Sarvam-1, a 2B Indic base model, in all six FLORES and IN22 directions (FLORES chrF 54.3 into Tamil and 55.2 into English, against 49.2 and 44.2), and nearly doubles its base model on native-Tamil IndicIFEval (19.3% from 10.0%). It is weak on knowledge: reading-comprehension and knowledge
benchmarks sit near chance, and on 50 held-out everyday questions written by one native speaker, one LLM judge rated 46% of its replies usable (22-24 of 50 over three passes; 95% interval for 23 of 50, 33-60%), with nearly every failure a wrong fact. Our two further SFT experiments changed answer format but not the knowledge measures. We also describe our first model, Agaram 1.5B, whose failures shaped the choices here; how the judge's scores varied between passes on identical replies; and, item by item, what the targeted rounds trained against and where frontier-model text entered the data. The project ran on compute credits and our own funds, about USD 13,300 across both models; the weights are released (licence to be announced after legal review), with GGUF files for llama.cpp, at https://huggingface.co/murai-labs/agaram-2.5b-instruct; code at https://github.com/Murai-Labs/Agaram2.5b
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Resource-Efficient 3D Shape and Orientation Estimation of Road Users using Roadside RGB Camera and 3D Radar
Shiva Agrawal, Savankumar Bhanderi and Gordon Elger
End-to-end deep learning pipelines for camera-radar 3D object detection are well established in driver assistance systems and autonomous vehicles; however, adapting them to roadside-mounted infrastructure presents significant challenges. On vehicles, sensor heights, pitch angles, and relative geometries remain largely uniform, allowing end-to-end models to generalize effectively. On the contrary, roadside sensor installations vary drastically in height, tilt, and field of view across locations, rendering end-to-end models prone to failure and difficult to adapt without massive location-specific
datasets. Hence, instead of designing a complex end-to-end pipeline for direct 3D bounding box estimation, a low-cost, resource-efficient two-stage approach is proposed for real-time 3D shape and orientation estimation. The first stage utilizes any off-the-shelf, state-of-the-art method to extract 2D camera bounding boxes and associated 3D radar points for each road user. The proposed second stage then processes these inputs to construct 3D oriented bounding boxes where radar data determines 3D position, predefined templates define size for each road user, and a tiny neural network predicts a site-specific and optimized yaw angle. The
algorithm is successfully validated at a curved road with a junction for pedestrians, bicycles, and cars, where it achieves 25 frames per second on an NVIDIA Jetson ORIN for real-time applications.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison
Pratuat Amatya, Vinay Setty, V Venktesh et al. (+1 more)
Large
Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL
alignment steps such as RLHF do not focus on factuality of LLMs, hence they may generate non-factual information, which could result in unintended consequences. In response, a number of factuality
alignment approaches have been proposed in the literature which claim to improve factuality of LLMs on their own
benchmarks. However, these methods have not been reproduced independently and are also not comparable since each uses a different base model, training data, evaluation set, judge, and metric. In this paper, we present the first independent reproduction of five factuality
alignment methods, which span on-policy RL (PPO, GRPO, and Dr.~GRPO) and offline preference optimization (DPO and KTO), and compare them on a common
benchmark with common evaluation metrics. We found that none of these methods reproduces in full, and on the common
benchmark none of the methods significantly outperforms the base model. On closer inspection, the rewards optimize for format, length, or brevity rather than factuality and relevance, whereas the choice between on-policy and offline training matters little. Furthermore, the evaluation metrics and
benchmarks are also part of the problem since they do not measure relevance of text to the
prompt. Since there is no ground truth associated with the
prompts, the reliance on LLM judges and
retrieval for verification also makes the evaluation fragile. We release our code, data, and checkpoints.
Read the full abstract ▾
All authors Pratuat Amatya, Vinay Setty, V Venktesh, Avishek Anand
Artificial Intelligence · Cross-listed from cs.LG
Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs
Mikhail Aleksandrov, Nail Bashirov, Maksim Ivanov et al. (+6 more)
Prompt-based adaptation offers several ways to specialize a frozen
language model, ranging from natural-
language prompt optimization to learned continuous
prompts. These methods are usually compared through downstream performance, although similar outputs need not arise from similar internal computations. We study how discrete
prompt optimization,
prompt tuning, and prefix tuning alter the processing of dense and mixture-of-experts
language models. Our analysis shows that the location of the adaptation predicts how task information is carried to the output: optimized text primarily changes response construction, input-level
prompts write their influence into content representations, and layer-wise prefixes maintain direct control through
attention. In MoE models, these differences further induce distinct expert-routing patterns. At the same time, common representation-level measurements respond strongly to generic context changes and do not reliably distinguish useful adaptations from matched placebos. We argue that understanding
prompt adaptation requires separating representation drift from the part of that drift that is aligned with, and causally used by, the model's task computation. This perspective provides practical guidance for selecting, evaluating, and interpreting
prompt adaptation methods.
Read the full abstract ▾
All authors Mikhail Aleksandrov, Nail Bashirov, Maksim Ivanov, Andrew Tsukanov, Timofey Karyagin, Alexander Miasnikov, Gleb Molodtsov, Valentin Samokhin, Aleksandr Beznosikov
Artificial Intelligence · Cross-listed from cs.IR
Federica Santi, Vasilije Marković, Daniel Scott et al. (+1 more)
Dense vector
retrieval can miss evidence connected through intermediate entities, while direct graph
retrieval requires access to the graph at query time. We compare five offline graph-based
embedding transformations and strategies for using the resulting graph-modified
embeddings alongside the originals, without query-time graph access. On a synthetic professional-network
benchmark with complete supporting-evidence sets, direct replacement of the original
embeddings reduces evidence recovery. Multi-stage strategies improve recovery by using graph-modified
embeddings to guide the search while retaining the originals for semantic relevance. On questions requiring linked facts or comparisons among candidates, the strongest configuration improves recovery by up to 25.9% relative to plain vector
retrieval. It also matches baseline recovery with 40% fewer returned nodes. Controls confirm that graph information contributes beyond multi-stage
retrieval alone. Across the tested methods,
retrieval performance depends more on how graph-modified
embeddings are used than on how they are produced.
Read the full abstract ▾
All authors Federica Santi, Vasilije Marković, Daniel Scott, Lazar Obradović
Artificial Intelligence · Cross-listed from cs.LG
PRISM: Calibrating Black-Box Judges with Counterfactual Probes
Kakei Yamamoto and So Kuroki
Large
language models are increasingly used as judges to reduce reliance on costly human evaluation, yet their scores can systematically disagree with human judgments. We ask whether responses to an explicitly imposed evaluative bias can help correct a judge's implicit scoring biases. We introduce PRISM (Probe-based Residual Inference of Scoring Misalignment), which holds the evaluated content fixed and measures score changes when attributes are emphasized or de-emphasized. A local sensitivity model motivates representing these responses as a surrogate Jacobian. Ridge regression on human labels learns a correction to the baseline score. The resulting scoring protocol is rubric-free: it uses overall scores without requesting criterion-level ratings. In the main Jev and Sol comparisons on SummEval summarization and HANNA story evaluation, PRISM and its learned-baseline variant significantly improve agreement with human rankings over uncalibrated scores while remaining competitive with rubric-based methods. A controlled SummEval comparison yields similar agreement for rubric-derived quality probes and style probes, supporting calibration without reproducing rubric criteria. The learned coefficients reveal shared and opposing correction directions across judges.
Read the full abstract ▾
Artificial Intelligence
Delegating Earth science model calibration to knowledge-guided LLM agents
Zhanliang Zhu, Ziwei Li, Liujun Zhu et al. (+3 more)
Applying process-based Earth science models to new sites and questions often requires expert calibration decisions. Reliable delegation to
language-model
agents must preserve scientific competence and reproducibility. Here we develop a general calibration harness (GCH) for end-to-end delegation from a calibration request to assessed results. Constrained by a knowledge infrastructure (KI) and a validation convention,
agents define parameter domains, observation mappings and objectives, and generate model-specific code. GCH checks the formulations against the same declarations and freezes them before numerical search and assessment, which require no further
agent judgement.
Agent-authored workflows executed across six model families, with assessment identifying unmet criteria. In snow-model tests, five of five knowledge-guided specifications executed on the first attempt, compared with none of five given only the model name, achieving validation Nash-Sutcliffe efficiency (NSE) of 0.81-0.94 against 0.57 for defaults. Under a common objective, independent GR4J formulations yielded scores within 0.001 NSE; re-evaluating eleven saved parameter vectors reproduced their metrics. In ten paired VIC tests with matched budgets, fixed search was non-inferior to continuing
agent proposals (margin, -0.02 NSE; median difference, -0.003). This separation enables end-to-end calibration delegation with inspectable scientific choices and reproducible numerical evaluation.
Read the full abstract ▾
All authors Zhanliang Zhu, Ziwei Li, Liujun Zhu, Yuchen Liu, Junliang Jin, Jianyun Zhang
Artificial Intelligence · Cross-listed from cs.CV
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
Yu Wang, Rui Dai, Wei Chen et al. (+5 more)
City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor scenes. We propose Urbex, an agentic
vision-
language framework that instead casts grounding as active spatial search. Urbex represents a city-scale 3D scene as an interactive multi-view environment, allowing a VLM
agent to query landmarks, zoom into local regions, render oblique views, and commit a grounded bounding box. We optimize this tool-use policy with reinforcement learning on CityRefer, using smooth localization rewards and lightweight shaping rewards for efficient exploration. Experiments show that Urbex achieves the best Hit@1 and IoU on CityRefer, supports candidate-free grounding without ground-truth boxes, and is substantially faster than the strongest city-scale ranking baseline. Zero-shot results on STPLS3D-Refer further indicate improved cross-scene robustness.
Read the full abstract ▾
All authors Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li
Artificial Intelligence
ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
Qiuyu Ding, Heng-Da Xu, Changda Xia et al. (+14 more)
We introduce ABot Embodied
Reasoning (ABot-ER), a unified embodied
reasoning foundation model that breaks the tension between breadth and depth in embodied
reasoning. Embodied intelligence demands the joint mastery of perception, planning, and execution, yet reconciling generality with specialization across this spectrum remains an open challenge. Within a single unified model, ABot-ER commands specialist-level depth across all three competencies, spanning spatial, scene, and temporal
reasoning in perception; long-horizon action organization in planning; and point grounding and affordance in execution. The Agentic Data-Model Self-
Evolution Engine continuously adapts data strategies to the model's evolving capability state. The Task-Conditioned Adaptive Training Strategy uses task
tokens to activate lightweight low-rank residuals over a shared backbone, separating updates from heterogeneous output formats while retaining shared embodied knowledge. Across a systematic evaluation on twelve
benchmarks covering three core competencies and five capability dimensions, ABot-ER achieves state-of-the-art overall performance across perception, planning, and execution within a unified parametric framework, demonstrating that breadth and depth can coexist in unified embodied
reasoning.
Read the full abstract ▾
All authors Qiuyu Ding, Heng-Da Xu, Changda Xia, Jiajun Shen, Zihao Guan, Zhengchen Yuan, Jianfang Zhang, Di Yang, Jiayi Tian, Yuting Xu, Fei Wang, Shiao Liu, Wei Zhang, Xiaolong Wu, Wenbin Tang, Zedong Chu, Mu Xu
Artificial Intelligence
Choosing LLMs for Strategic Agent Interactions
Arastun Mammadli, Herbert Woisetschläger, Jawad Fayaz et al. (+1 more)
Game-theoretic
benchmarks claim that large
language model (LLM) strategic decision-making varies across game types, interaction structures, and capability dimensions. However, they only evaluate strategic performance across individual fixed models. In parallel, contemporary LLM routers pick models under quality-cost trade-offs, but with no notion of a strategic structure. They do not account for an opponent that might be unknown, and that can adapt over time and shift the feedback signal. To address this, we extend the game-theoretic evaluations and define strategic selection as the meta game layered on top of the base game. In each round, a strategic selector fields an LLM from a portfolio of models to navigate a game payoff
matrix that is latent and learned online. We find that the evaluation signal is game-specific, and that extracting a reliable signal requires a much higher number of seed runs $N$ compared to traditional benchmarking setups. Evaluating across 5 games and 10 LLMs, we show a model's strategic competence varies significantly depending on the game setup and the opponent faced. Building on this, we implement a suite of selector methods and find that approaches that rely on query
embeddings or LLM self-reflection do not consistently capture the underlying strategic signal. A lightweight multi-armed bandit
algorithm performs more reliably across games, though it still falls short of the best fixed model. Finally, we show that simple non-stationary and
adversarial bandit variants fail to outperform a stationary bandit baseline, pointing to a gap in how current methods handle a shifting opponent in strategic settings.
Read the full abstract ▾
All authors Arastun Mammadli, Herbert Woisetschläger, Jawad Fayaz, Shiqiang Wang
Artificial Intelligence · Cross-listed from cs.RO
Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation
Youpeng Wen, Gang Wang, Tianyu Huang et al. (+5 more)
A
robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes. It must also maintain awareness of task progress and determine when to advance. To address these challenges, we introduce Orchestra, an
agent harness that separates task planning and execution management from action generation. Orchestra decomposes a complete
multimodal instruction into ordered subtasks, tracks completed steps, and updates the locations of relevant objects and destinations during execution. It maintains a shared context containing the active subtask, spatial grounding, and recent observations. An action policy uses this context to generate actions, while a separately trained progress evaluator estimates when to advance to the next subtask. To evaluate whether
robots trained on atomic instructions and short trajectories can execute longer subtask sequences, we introduce a
benchmark named RMBench-Compose. Orchestra achieves a mean success rate of $68.22\%$ across nine RMBench tasks, outperforming Mem-0 by $26.22$ percentage points. On RMBench-Compose, it achieves an Average Success Length (ASL) of $7.35$ subtasks, $2.46$ times that of HarnessVLA. Across four real-world multi-step tasks, it improves mean ASL by $25.0\%$ over Orchestra using the base $\pi_{0.5}$ policy. These results show that Orchestra helps
robots carry out longer sequences of subtasks while preserving the requested subtask order and acting on the specified objects. Our code and project page are available at https://youpengwen.github.io/Orchestra.
Read the full abstract ▾
All authors Youpeng Wen, Gang Wang, Tianyu Huang, Weiwei Zhang, Zhijian Huang, Wei Chen, Xieyuanli Chen, Yunhui Liu
Artificial Intelligence · Cross-listed from cs.CL
Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and English
Jophin John, Michael Hoffmann, Piroska Lendvai et al. (+1 more)
Post-training quantisation reduces the
memory cost of large
language models, but it remains unclear whether compression preserves
language skills of regional varieties as reliably as their standard-
language counterparts. We study this question for Bavarian, Standard German, and English using BAVGROUND, a multiple-choice
benchmark, where 206 source questions are aligned across all three
languages. Across 14 open-weight 7B–10B instruction models, we compare BF16 with 8-bit GPTQ and two 4-bit settings, GPTQ and AWQ. Eight-bit GPTQ remains close to BF16 and largely preserves the relative behaviour of the three
languages, while 4-bit quantisation was found to be much less stable. The two 4-bit methods reduce average accuracy by about 1.4–1.5 percentage points and change 11.9–16.0% of BF16 decisions, with changes concentrated on examples where the BF16 model is already uncertain. This instability does not translate into a consistent Bavarian disadvantage. Although Bavarian, a low-resource dialect, has lower baseline accuracy than German and English, the
language most affected at 4 bits varies across models and quantisation methods. Calibration further shapes these cross-
language effects: the relative Bavarian–German effect changes with calibration
language, while changing the calibration source has little average effect on GPTQ-4 but can affect AWQ-4 much more strongly. Free-form evaluation on five models further shows that 4-bit compression can degrade generated responses even in settings where multiple-choice accuracy changes only modestly, while 8-bit GPTQ remains comparatively stable. Overall, our results show that quantisation robustness for regional
language varieties depends on the model, quantisation method, calibration data, and evaluation setting, and cannot be measured by aggregate multilingual accuracy alone.
Read the full abstract ▾
All authors Jophin John, Michael Hoffmann, Piroska Lendvai, Florent Dufour
Artificial Intelligence
AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents
Xiangrui Liu, Shuo Tang and Siheng Chen
Training business automation
agents requires executable tasks that connect a natural-
language request to an application state and a verifiable end state. Traditional Rubrics requires Authors to recreate application interfaces, initial records, policy evidence, and outcome checks for each task, entangling business logic with repeated infrastructure work. We introduce AssetForge, an asset-augmented task-construction pipeline that pairs a reusable construction-asset library with task-specific Rubrics. The assets provide application interfaces, world-state components, policy/evidence carriers, and native assertion definitions; the Rubric directs their instantiation for a particular business task. Executable checks and an additional model-based review validate each candidate, return targeted feedback, and support bounded repair before acceptance. On AutomationBench v1.0.6 public-600, fine-tuning Qwen3.6-35B-A3B on 6,000 AssetForge examples yields 41.17% on the official strict pass@1 metric, 4.4 times the 9.33% base score (+31.83 points). With the same backbone and GLM-5.3 supervision, AssetForge reaches 41.17% versus 30.33% for traditional Rubrics, a 10.84-point gain (35.7% relative) at the same accepted-example scale (6,000 versus 6,000 examples). Both DeepSeek- and GLM-supervised AssetForge models improve AppWorld completion over the base model on Test-Normal and Test-Challenge. These results establish the advantage of AssetForge's complete construction pipeline on AutomationBench public: the coupled asset-Rubric interface directs Authors toward business logic, while executable checks and model-based review validate their tasks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On
Yuhan Li, Zhiyu Jin, Yifan Tong et al. (+5 more)
Virtual footwear try-on (VFTON), a critical yet underexplored area in virtual try-on (VTON), aims to synthesize faithful try-on results given diverse footwear and model images while maintaining 3D consistency and texture authenticity. Unlike conventional garment-focused VTON methods, VFTON presents unique challenges due to (1) Data Scarcity, which arises from the difficulty of perfectly matching product shoes with models wearing the identical ones, (2) Viewpoint Misalignment, where the target foot pose and source shoe views are always misaligned, leading to incomplete texture information and detail distortion, and (3) Background-induced Color Distortion, where complex material of footwear interacts with environmental lighting, causing unintended color contamination. To address these challenges, we introduce MVShoes, a multi-view shoe try-on
dataset consisting of 7305 well-annotated image triplets, covering diverse footwear categories and challenging try-on scenarios. Furthermore, we propose a dual-stream DiT architecture, ShoeFit, designed to mitigate viewpoint misalignment through Multi-View Conditioning with 3D Rotary Position
Embedding, and alleviate background-induced distortion using the LayeredRefAttention which leverages background features to modulate footwear latents. The proposed framework effectively decouples shoe appearance from environmental interferences while preserving high-quality texture detail through decoupled denoising and conditioning branches. Extensive quantitative and qualitative experiments demonstrate that our method substantially improves rendering fidelity and robustness under challenging real-world product shoes, establishing a new
benchmark in high-fidelity footwear try-on synthesis.
Read the full abstract ▾
All authors Yuhan Li, Zhiyu Jin, Yifan Tong, Wenxiang Shang, Benlei Cui, Xuanhong Chen, Hangcheng Zhu, Bingbing Ni
Artificial Intelligence
Complex materials engineering via Provenance Action Graphs: potential, structure and demonstration
Yevgeny Rakita, Paul Todd, James R. Neilson et al. (+1 more)
This work discusses and tests the potential of reaction graphs for material synthesis, in which events consist of reaction steps (actions) and their outputs (observations). The importance comes from the requirement to synthesize technologically useful materials, especially those that are kinetically stabilized. Often, it is a science that follows years of trial and error, culminating in (published) successful recipes, but is truly driven by far more (unpublished) failures. The entry into the era of AI provides an opportunity to use learning
algorithms to encode rules from multi-dimensional synthesis pathways, regardless of their technological usefulness, and to decode both forward prediction and inverse learning modes. The main incentive is to accelerate material discovery by generating a global knowledge base that can be shared among data
agents and contributed to by them. We will focus on several scenarios in the common synthesis process during solid-state synthesis, primarily because these reactions are kinetic in nature and require closer monitoring and control of the reaction history.
Read the full abstract ▾
All authors Yevgeny Rakita, Paul Todd, James R. Neilson, Simon J. L. Billinge
Artificial Intelligence · Cross-listed from cs.CL
SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems
Erfan Shahabi, Amirhossein Roshandel, Mohammad Sadegh Sadeghi et al. (+1 more)
Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation. LLM-based simulators have made realistic simulation possible but typically condition on profiles derived from explicit ratings, demographics, and static sources capturing surface preferences while omitting implicit behavioral characteristics such as decision-making style, aspect-level preferences, and domain expertise. We propose SimInter, a pipeline that elicits these attributes via synthetic interviews between two LLM
agents, grounded in the user's statistical profile and historical conversational evidence. Before profile enrichment, an audit
agent explicitly flags potential fabrication and stereotyping at the turn level. We instantiate and evaluate SimInter on movie recommendation. We simulate 300 ReDial users and, on a matched subset of 100 users, compare SimInter with a statistics-only baseline: SimInter significantly increases the diversity of expressed preference aspects (filtered aspect
entropy: 1.619 vs. 0.859; paired d = 0.96, Holm-adjusted p < 0.001). This gain persists when the simulator converses with two trained recommenders, KBRD and UniCRS, under two independent evaluation judges (+0.28 to +0.56 nats; all p < 0.001). Human evaluation finds 94.3% of enriched-attribute claims supported or partially supported, while human judgments agree with 95.2% of the auditor's binary filtering decisions on a stratified sample.
Read the full abstract ▾
All authors Erfan Shahabi, Amirhossein Roshandel, Mohammad Sadegh Sadeghi, Azadeh Shakery
Artificial Intelligence · Cross-listed from cs.CV
AffectWorld: Benchmarking Emotion-Driven Future World Prediction
Changhao Song, Yacong Chen, Hui Gao et al. (+2 more)
The world encompasses both physical environments and human actors. Predicting its
evolution requires understanding both physical laws and how emotions shape human actions. However, existing world model
benchmarks primarily assess physical plausibility and perceptual quality, leaving emotion-driven world
evolution largely untested.We introduce AffectWorld, a
benchmark that evaluates the chain Emotion-Action-World State through three tasks: World-State Consistency, Emotion-Action Consistency, and Causal Consistency. It comprises 1,498 everyday
video samples annotated with plausible emotions, action tendencies, and atomic world-state constraints. A counterfactual subset of 233 samples tests whether changing an
agent's emotion under fixed scene and event conditions yields corresponding changes in actions and consequences. We define eight metrics across the three tasks and an additional counterfactual metric, combining automatic visual assessment with human-calibrated VLM/LLM judgments. Evaluations of five SoTA world models (e.g., Cosmos3) required world-state change scores of 0.100-0.280 and counterfactual emotion sensitivity scores of 0.027-0.070 on a [0, 1] scale. These results reveal substantial gaps in generating the consequences of emotion-driven actions and adapting future predictions to emotional interventions. AffectWorld provides a testbed for advancing world models that capture how emotions shape future physical and social states.
Read the full abstract ▾
All authors Changhao Song, Yacong Chen, Hui Gao, Yazhou Zhang, Peng Zhang
Artificial Intelligence
Efficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction
Md Asiful Islam, Fahmida Alam and Mihai Surdeanu
Guardrail approaches that rely on
reasoning-based large
language models (LLM) improve safety decisions, but come with substantial inference overhead due to the explicit
reasoning. We introduce LR-Guard (Latent
Reasoning Guardrail), an efficient and explainable guardrail that jointly learns structured latent
reasoning and on-demand
reasoning reconstruction. Our method distills a frozen teacher's analysis of safe and unsafe
prompt interpretations and their comparison into compact latent representations. Joint training optimizes these representations for both safety prediction and reconstruction of the teacher's explicit
reasoning traces, enabling human-readable explanations without requiring intermediate text generation for every decision. Experiments show that LR-Guard outperforms its explicit-
reasoning teacher in most in-domain and out-of-domain settings on safety classification and explanation extraction, while achieving a 19.4x inference speedup at batch size one. Further, reconstructed
reasoning traces from the latent information exhibit high semantic similarity to the teacher's explicit
reasoning.
Read the full abstract ▾
Artificial Intelligence
A dataset of formalised theorem statements from the Annals of Mathematics
Thomas Browning, Katerina Hristova, David Ledvinka et al. (+4 more)
Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires
datasets of formal statements that are both hard and trustworthy. We present AnnalsChallenge: 50 formalised
theorem statements written by hand in Lean 4 using Mathlib. Each is the main result of a paper published in the Annals of Mathematics since 2020. Every formalisation was manually reviewed and then audited by AI. We release them without formalised proofs.
Read the full abstract ▾
All authors Thomas Browning, Katerina Hristova, David Ledvinka, Justus Springer, Hang Lu Su, Jack McKoen, Kevin Buzzard
Artificial Intelligence
Output Discipline Sets the Floor: A Falsification-Guided, Model-Agnostic Agent Protocol for Auditable Hypothesis-Driven Decision Making
Jing Liu, Yongxing Qi, Ping Yao et al. (+1 more)
What binds large
language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence? On the public TCMEval-SDT
benchmark for Traditional Chinese Medicine syndrome differentiation (200 cases), the binding constraint is output discipline and
reasoning structure, not model capability alone: two years of model scaling move zero-shot scores by only -0.03 to +0.08, while output-discipline failures (non-terminating
reasoning, format non-compliance, large run-to-run spread) persist even in frontier models. We test this with a model-agnostic
agent framework formalizing decision making as a five-stage closed loop, enforced by a candidate x evidence
matrix falsification protocol: every candidate is judged against every evidence item, at least half of the candidates must be falsified before a conclusion is licensed, and survivors are emitted in a machine-verifiable single-line format. Across five base models, the effect is sign-conditional on zero-shot output discipline: it rescues models whose discipline fails (DeepSeek-V4-Flash: +0.267/+0.271, entirely termination rescue), reduces a high-variance model's run-to-run standard deviation from 0.218 to 0.007 (Kimi K3), and significantly costs already-disciplined models (-0.087 to -0.120 on budget-matched Qwen3-4B/32B). Ablations attribute the cost to the candidate-bounded format layer and show the effect is independent of injected knowledge content (protocol-knowledge decoupling). The protocol also transfers to misinformation-robust mathematical
reasoning, detecting injected false premises at 89.8% recall with a 6.8% false-positive rate (MCC 0.54; a flag-everything baseline scores 0) and restoring accuracy to the no-misinformation ceiling. Where zero-shot output discipline is weak, the
reasoning protocol sets the floor; base-model capability always sets the ceiling.
Read the full abstract ▾
All authors Jing Liu, Yongxing Qi, Ping Yao, Ting Wu
Artificial Intelligence · Cross-listed from cs.LG
Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller
Sagi Habani, Yehonathan Refael and Ofir Lindenbaum
Releasing a neural network checkpoint can leak information about its training data, and existing reconstruction results rely on gradient-descent training. We ask whether the choice of optimizer affects the ability to recover the training data. Extending work connecting Karush–Kuhn–Tucker conditions to training-data reconstruction, we show that the implicit biases of popular optimizers (SGD, Adam,
Muon) leave very different fingerprints of the training data. We argue that the key distinction is the weight-specificity of these implicit biases, namely how much continuous information about the final weights the optimizer-dependent target of the stationarity conditions encodes. The limiting stationarity conditions for models trained with SGD and
Muon retain enough weight-specific information to reconstruct training examples in practice. For Adam in the $\ell_\infty$ implicit-bias regime, the optimizer-dependent part of these conditions encodes only a discrete pattern of maximal coordinates and their signs, and at nondegenerate KKT points the conditions are too few to identify the training set to first order. Experiments on MNIST and CIFAR-10 support these claims: models trained with
Muon can yield stronger reconstructions at much lower training cost than models trained with SGD, although this advantage depends on the training regime and architecture, and models trained with Adam appear consistently more resistant to the evaluated attacks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
JevGPT: Thinking Fast and Slow in Autonomous Research
Yasheng Sun, Yanning Dai, Yimeng Chen et al. (+9 more)
Autonomous research
agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between
retrieval coverage and the evidence that informs research. The challenge is to align fast local judgments with changing evidence needs and feed their findings back into research decisions. We introduce JevGPT, a dual-system architecture for autonomous research that couples fast evidence processing with deliberative research planning. System Two sets evidence objectives and integrates findings, while System One locates support, assesses relevance, and guides further inspection. Independent source judgments run in parallel; selected original passages inform the next research step. Experiments on fixed-corpus question answering and document ranking show that JevGPT achieves leading task performance, with faster completion and lower cost than comparably effective research
agents. Evidence analysis shows broader source inspection and greater coverage of supporting documents in the research loop, highlighting efficient evidence processing as a route to more capable autonomous research.
Read the full abstract ▾
All authors Yasheng Sun, Yanning Dai, Yimeng Chen, Nanbo Li, Firas Laakom, Yifan Xu, Piotr Piękos, Mateusz Ostaszewski, Wenyi Wang, Cheng Luo, Yuhui Wang, Jürgen Schmidhuber
Artificial Intelligence · Cross-listed from cs.CR
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Yan-Lun Chen, Pin-Yu Chen and Chia-Mu Yu
Third-party skills can expose LLM
agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such instructions in skill files for
agents to decode and follow. We evaluate Caesar and layered variants across eight models and 139 injection-task pairs, separating instruction recovery from attack success. In the primary setting with shortened skills, the variants achieve attack success rates of up to 47.5% and 40.3%, respectively. Successful decoding does not guarantee attack success, and layering has model-dependent effects. The tested skill scanners rarely flag injected skills. These findings highlight the risk of promoting decoded, untrusted content into actionable instructions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
FALLNEST: Dual-Domain Dataset Condensation of Imbalanced IMU Data for Wearable Fall Detection
Rashi Niyas P, Ritika Jain and Hitika Tiwari
Wearable fall detection is hampered by rare fall events, scarce labeled IMU data, and the cost of training deep models on large, imbalanced corpora. Existing methods either rely on hand-crafted features with shallow classifiers, which limits learning from raw signals, or train deep networks on full
datasets that require re-sampling to counter class skew and demand substantial data and compute. To address this, we propose a novel Fall detection framework via Normalized-gradient and
Embedding matched Synthetic Time-frequency condensation, dubbed FALLNEST, a data-centric approach that distills large, imbalanced IMU
datasets into tiny, class-balanced synthetic training sets. Building on dual-domain time-series condensation (CondTSC), FALLNEST introduces a fall-specific 7-channel input with accelerometer vector magnitude, class-balanced K-Means initialization, and normalized gradient matching with gradient clipping, combined with MMD-based
embedding alignment and multi-view
Fourier-domain augmentation, so that class balance arises from the condensed set itself rather than from re-sampling. We evaluate on SisFall, KFall, and MobiFall using strict subject-wise splits and naturally imbalanced test sets, reporting accuracy, Macro-F1, and PR-AUC over five seeds. A 102K-parameter TinyCNN trained on only 32 to 146 synthetic windows (about only 1% of the training windows) reaches 93.5-95.8% mean accuracy and 0.89-0.98 PR-AUC, with standard deviations of 1.0-1.7% in accuracy, demonstrating the efficacy of our approach.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
LiFUSE: Frequency-Spatial Unified Self-Supervised Pretraining for Liver Disease Analysis on Non-contrast CT
Hao Zhang, Yi Huang, Wei Liu et al. (+6 more)
Given the growing global burden of liver tumors and diffuse liver diseases, non-contrast computed
tomography (NCCT) is increasingly used for opportunistic screening because of its low cost and favorable safety profile. However, downstream tasks such as tumor detection and fine-grained disease diagnosis remain challenging due to NCCT's inherently low tissue contrast, lack of hemodynamic enhancement, and complex anatomical background. These limitations make subtle, heterogeneous, and multifocal hepatic lesions difficult to identify. Although large-scale self-supervised pretraining can learn robust representations from unlabeled NCCT scans, conventional voxel-wise reconstruction does not fully exploit the complementary information available in NCCT. Under weak NCCT contrast, low-level intensity patterns become less informative for pathology recognition, limiting the capture of lesion-specific discriminative features. In this paper, we propose the Liver Frequency-Spatial Unified Self-Supervised Pretraining (LiFUSE). The frequency branch applies random band-stop masking and spectrum reconstruction to encourage the model to capture subtle differences between lesions and surrounding tissues, while the spatial branch performs hybrid-granularity masked volumetric reconstruction to accommodate lesions of diverse sizes and morphologies. Finally, a cross-domain consistency scheme couples the spatial and frequency branches, yielding more discriminative representations for hepatic structures and lesions. Extensive experiments on three clinically relevant tasks across internal cohorts and a public target-domain transfer setting show that LiFUSE consistently outperforms strong baselines. These results suggest that unified frequency-spatial learning can improve liver disease analysis on NCCT, highlighting its potential for large-scale screening.
Read the full abstract ▾
All authors Hao Zhang, Yi Huang, Wei Liu, Yuan Gao, Zeju Li, Xu Han, Yu Shi, Ling Zhang, Ke Yan
Artificial Intelligence
Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
Dezheng Bao, Sihang Du, Renhong Huang et al. (+3 more)
Multi-
agent debate (MAD) aims to improve large
language model
reasoning by exposing
agents to alternative solutions and enabling iterative revision. However, standard broadcast-style MAD makes peer answers visible without requiring
agents to engage with a particular peer claim. As a result, reliable
reasoning may be suppressed by conflicting or majority responses, limiting achievable performance, while erroneous
reasoning may persist and degrade final predictions without actionable feedback. We propose TrueMAD, a backbone-agnostic test-time plug-in that introduces one-to-one, free-form peer advice between answer broadcasting and self-revision. Each source
agent responds to a target's current
reasoning through support, rebuttal, refinement, or further questions, while the target retains control over how to revise. The same mechanism can augment standard MAD and its improved variants without parameter updates. Across AIME, GPQA-Diamond, and TruthfulQA with Qwen3-30B-A3B, TrueMAD improves
agent-level and strict-majority accuracy over MAD by 3.62 and 3.52 percentage points on average, while TrueDMAD improves DMAD by 4.72 and 4.06 points, respectively. Analyses at the utterance,
agent-transition, and group levels further show more peer-specific deliberation, more correction-oriented revisions, and more favorable consensus dynamics.
Read the full abstract ▾
All authors Dezheng Bao, Sihang Du, Renhong Huang, Zhizhang Yuan, Yifei Sun, Yang Yang
Artificial Intelligence · Cross-listed from cs.CV
Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory
Qian Chen, Xianyin Zhang, Lifan Guo et al. (+1 more)
Vision-
language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as
retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models indicate heading levels using different numbers of preceding “\#” symbols, page-by-page prediction often lacks document-level consistency. In practice, input-resolution and context-length constraints make it infeasible for a VLM to jointly process all page images in documents containing tens or hundreds of pages. To address this limitation, we propose a VLM-based framework that incrementally reconstructs heading hierarchies with a level-wise
multimodal memory. The
memory retains a compact subset of all previously processed pages, selected by anchors. Our framework supports flexible anchor selection, and in this work we select the most recent node at each level, allowing the VLM to observe the visual, textual, and layout patterns of headings at every level. For comprehensive evaluation, we also introduce the Complex and Long Document Heading Hierarchy Reconstruction
Benchmark (CLDoc-HHRBench), comprising 250 documents and 11,212 pages with expert-verified annotations. Experiments on CLDoc-HHRBench and three existing
benchmarks demonstrate the effectiveness of our method.
Read the full abstract ▾
All authors Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang