Computation and Language
Doc2LoRA Provides Decodable Representations of Scientific Ideas
Chand Sahil Mansuri, Joel Zachariah and Sadamori Kojaku
Representing scientific papers as points in a space lets us search for similar papers and inquire about how fields relate to one another and drive innovation. Beyond search, the vector space of papers invites generation: mixing papers through simple vector operations creates new points, mirroring combinatorial novelty, the recombination of existing ideas into new ones. However, a mixed point often represents an idea no paper has yet realized, with no papers nearby to identify the idea. We propose representing each paper by a LoRA adapter generated by the Doc-to-LoRA hypernetwork. Every point in the space, including mixtures, thus represents a large
language model (LLM) open to questions and instructions in natural
language. On papers from the American Physical Society (APS), we instruct the LLM at the average of each subfield to name the field in a few words and obtain labels closer to the official names than the labels of five baselines, as judged by word overlap and a panel of five LLM judges. We also ask the LLMs at points between two APS papers to write an abstract and obtain descriptions shifting from one paper to the other in step with the mixing weight. While Doc-to-LoRA is trained for generation, a small invertible transform makes the
embeddings competitive for search, on par with SPECTER2 and EmbeddingGemma and close to SBERT. Because the transform is invertible, every point in the transformed space still maps back to an LLM. The
embeddings thus serve both search and generation, enabling researchers to question the idea at any point in the space as a starting point for generating new ideas.
Read the full abstract ▾
Artificial Intelligence
Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
Qiankai Xu
A harness is the code around a
language-model
agent that organizes
prompts, calls tools, manages context, and controls execution. As models grow stronger, recent work has begun to let
agents improve their own harnesses, a line of work known as self-evolving harnesses. In most existing methods, a separate proposer running on a human-designed harness modifies the solver's harness, and a separate harness is evolved for each
benchmark. Real-world tasks come from many domains, so both the
evolution and the evaluation of a harness should cover a diverse range of tasks. We propose a framework close to recursive self-improvement: the same frozen model, on the same version of the harness, first solves tasks as the solver and then, as the proposer, reads the complete run records and directly edits the harness that runs it. Each
evolution batch draws tasks from five
benchmarks in different domains. To measure generalization, training and held-out tasks are strictly separated, and we additionally evaluate on five out-of-distribution
benchmarks never used during
evolution. We frame the
evolution process as deep-learning training with two stages, multi-task pretraining and continual training. Starting from a 49-line seed harness, the harness obtained at the end of the first stage improves the average score by 4.48 points on the in-distribution
benchmarks and by 12.64 points on the out-of-distribution
benchmarks, surpassing Codex on the former and matching it on the latter. In the second stage, continued
evolution on Claw-Eval, one of the out-of-distribution
benchmarks, further raises the score on that
benchmark from 66.17 to 68.06, exceeding Codex. We also provide an in-depth analysis of the mechanisms that emerged during
evolution, including output truncation, history compaction, and independent review.
Read the full abstract ▾
Robotics
TALK-Dem: Benchmarking Embodied Task Planning under Dementia-Associated Communication Patterns
Guangxin Zhao, Yiran Hu, Yuan Cao et al. (+7 more)
Existing LLM-driven
robot task planners rely on a taken-for-granted assumption of an ideal user whose instructions are clear, complete, and task-focused. However, when interacting with real-world users, especially those experiencing cognitive impairments, such as people living with dementia (PLWD), the planners often make mistakes and even pose physical safety risks. We proposed TALK-Dem (Talking Attributes and Linguistic Knowledge in Dementia), the first
benchmark for evaluating LLM-driven
robot task planning under dementia-associated verbal communication. TALK-Dem contains 4,800 instructions and covers five typical communication patterns, including Referential Imprecision, Object Substitution, Empty
Speech, Topic Drift, and Intrusion, at three intensity levels. Experiments across six open-weight LLMs reveal a substantial robustness gap. Across communication patterns, open-weight models exhibited performance drops of up to 22.3 percentage points compared to ideal instructions. This revealed a critical gap and even danger for real-world applications, especially in assistive robotics, where locally deployable models are necessary due to
privacy concerns and connectivity constraints. To mitigate this issue, we proposed the Context-Aware
Retrieval from Experience (CARE) method, which retrieves relevant previously resolved tasks to provide task-specific interpretation and planning context. CARE generally outperformed standard prompting baselines across the six open-weight models, improving average task success by 18.1 percentage points over the vanilla
prompt. These results highlighted the importance of both evaluating communication robustness and developing effective adaptation strategies for locally deployable assistive
robots. The TALK-Dem
dataset is publicly available at https://anonymous.4open.science/r/TALK-Dem-A6B3/.
Read the full abstract ▾
All authors Guangxin Zhao, Yiran Hu, Yuan Cao, Chenxi Jiang, Jianfei Yang, Yegang Du, Yasuyuki Taki, Yoshifumi Kitamura, Lin Gu, Zhi Zheng
Numerical Analysis
An Approximate Method for Modeling Plasmons on Graphene with Time- and Space-dependent Properties
Kaleigh Rudge and Fadil Santosa
This paper presents approximate computational methods for modeling surface plasmon propagation on a
graphene sheet with time- and space-dependent material properties. Starting from Maxwell's equations, the
evolution of current density under a spatially and temporally modulated Drude weight is formulated as a partial integro-differential equation (PIDE). Assuming small-amplitude perturbations of the Drude weight, a regular perturbation expansion is developed. The solvability and
Fourier invertibility of the resulting order-by-order integral equations are established in appropriate Sobolev spaces. A numerical solver combining a Volterra integral equation formulation with the fast
Fourier transform (FFT) is introduced, along with pointwise error estimates and computational complexity analysis. Additionally, an analytical transform-based solution using contour integration and Laplace inversion is derived for traveling-wave Drude weight modulations. Numerical simulations demonstrate diverse wave phenomena, including traveling, standing, and exponentially growing plasmonic current densities.
Read the full abstract ▾
Artificial Intelligence
Can an AI Agent Rediscover a Blaschke-Curve Invariant?
Yunus E. Zeytuncu
We study generalized Blaschke curves as a controlled environment for AI-assisted mathematical rediscovery. For one fixed degree-four Blaschke product, an
agent receives numerical coordinates of the six pair-lines determined by each of 80 boundary configurations. The target
theorem is withheld from the task instructions. The saved research log reports rejected
geometric hypotheses and a homogeneous cubic fitted to polygon sides. Its frozen coefficients predict 480 lines from 80 unseen parameter values, with a recorded RMS scale-free residual of $8.88\times10^{-17}$. Discovery-set diagonals provide an out-of-fit consistency check, not a fully held-out test. A separate one-configuration run reports insufficient evidence for invariance. A post-review deterministic degree-search baseline also recovers the cubic, so the experiment does not establish an advantage over
polynomial fitting. We present this single-instance case study as a protocol for separating
conjecture, numerical validation, and proof, with explicit limitations concerning
agent metadata, prior knowledge, and reproducibility.
Read the full abstract ▾
Computer Vision
Composition, Not Conversation: VLMs Lose the Scene, Not the Thread
L. D. M. S. Sai Teja, Ufaq Khan, N. Siva Gopala Krishna et al. (+5 more)
Vision-
language models (VLMs) increasingly reason over visual evidence that is cropped, segmented, retrieved, or revealed over time. Yet most VQA
benchmarks present the complete image and question at once. We ask what models lose when the same information is fragmented. We introduce Layered-VQA, with 93 scenes and 300 questions. Each image is decomposed into ordered RGBA layers that exactly recompose the original scene, and each question is annotated with supporting, minimal-sufficient, and distractor layers. We evaluate eleven open-weight VLMs from 3B to 32B parameters and two proprietary models with a scale of 187,200 conversations, graded by 1.74M open-model cross-judgments. We find three consistent failures. Loss in Composition: fragmenting the question has a small effect, but fragmenting the scene substantially reduces accuracy; recomposing the same layers largely restores performance. Oracle Inversion: even oracle-selected sufficient evidence can perform worse than the complete scene. Loss in Grounding: as more evidence is required, grounding degrades much faster than answer accuracy. Together, these results show that having the right visual evidence is not enough. How that evidence is composed and presented determines whether models can use and ground it. The right evidence is not enough: VLMs need the scene it came from.
Read the full abstract ▾
All authors L. D. M. S. Sai Teja, Ufaq Khan, N. Siva Gopala Krishna, Satyajit Tourani, Ashshak Sharifdeen, Fida Mohammad Thoker, Bernard Ghanem, Muhammad Haris Khan
Data Structures and Algorithms
Certifiable Near-Optimality: A Simple Framework for Unifying Search and Refutation for (Semi)random CSPs
Prashanti Anderson, Peter Manohar and Jeff Xu
A classical problem in average-case complexity is the study of random constraint satisfaction problems (CSPs). Random CSPs are traditionally studied in two different settings: refutation, where the instances are uniformly random and thus unsatisfiable with high probability, and search, where the instances are drawn from a planted model so that they are satisfiable. While there is no formal relationship between the refutation and search variants of random CSPs, known
algorithms are strikingly similar with near-identical computational thresholds. In this work, we establish a formal relationship between the known
algorithms for refutation and search by showing that in either case they achieve a stronger guarantee: they output an assignment $x$ along with a certificate $\pi$ that the fraction of constraints satisfied by $x$ is within some small $\varepsilon$ of the optimal assignment. We call this guarantee certifiable $\varepsilon$-optimality. As an application, we design new
algorithms for a model of semirandom CSPs where the instance hypergraph (or scopes) is random, but the literal negation patterns are adversarially chosen and may depend on the hypergraph. For such CSPs, we give a family of
algorithms that output certifiably $\varepsilon$-optimal solutions. We additionally study such semirandom CSPs in the "strong contamination model", where an adversary is allowed to corrupt an $O(\delta)$-fraction of constraints after seeing the initial CSP. For such CSPs, we give an
algorithm to output a certifiably $O(\delta)$-optimal solution.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ML
Acceleration of Diffusion Language Model through Discrete Average Generator
Yidong Ouyang, Zhengyan Wan, Themis Haris et al. (+8 more)
Discrete
diffusion models and flow matching have emerged as powerful frameworks for generative modeling over discrete state spaces, yet efficient few-step generation remains a fundamental challenge. In this work, we introduce the Discrete Average Generator, a principled extension of MeanFlow to Continuous-Time Markov Chains (CTMCs). Analogously to how MeanFlow defines an average velocity field over a time interval in continuous spaces, we define an average generator as the normalized increment of the transition kernel over a time interval. We show that this average generator satisfies a self-consistency identity, which provides the foundation for our training objective. We further develop training strategies that align with the standard training paradigm of
diffusion language models while keeping the resulting objective tractable. When projected onto per-coordinate marginals, the self-consistency identity admits a closed-form expression, enabling efficient training and inference. In Potts model simulations, our objective reduces the total variation distance of the $K$-step sampler by up to 67%. On OpenWebText, our method achieves the lowest generative perplexity among the evaluated methods for 8 to 64 sampling steps while enabling a $16\times$ acceleration, and achieves comparable performance to existing methods on ImageNet.
Read the full abstract ▾
All authors Yidong Ouyang, Zhengyan Wan, Themis Haris, Tian Tan, Liqian Peng, Henry Li, Ziqian Lin, Jianhang Chen, Maryam Karimzadehgan, Alec Go, George Michailidis
Machine Learning
Simulator-Refined Diffusion for Radio-Frequency Inverse Design
Jinhao Liang, Jacob K. Christopher, Michael Frei et al. (+2 more)
Diffusion models have shown potential in inverse design of printed
circuit boards (PCBs), enabling the generation of layouts conditioned on target S-parameters. Despite this promise, applying
diffusion models to PCB layout generation remains challenging due to their difficulty in meeting the quantitative electromagnetic specifications. A common approach is gradient-based guidance, which biases the
diffusion sampling process with the gradient of an objective used for evaluation. However, full-wave electromagnetic simulators are accurate but expensive and typically non-differentiable, whereas differentiable surrogates are informative but not always reliable. To address these limitations, this paper proposes Simulator-Refined
Diffusion (SRD), a novel combination of a low-fidelity differentiable surrogate and a high-fidelity non-differentiable simulator within the
diffusion sampling process. Unlike standard zeroth-order optimization, which requires a great number of random perturbations, our approach uses the surrogate's gradient to propose the perturbation direction while the simulator then searches based on this direction to identify an effective design update. Experimental results across different settings show that this method consistently outperforms current state-of-the-art methods, producing layouts whose simulated S-parameters match the target specifications up to 21.2% closer for in-distribution targets and up to 19.8% for out-of-distribution targets.
Read the full abstract ▾
All authors Jinhao Liang, Jacob K. Christopher, Michael Frei, Tommaso Dreossi, Nando Fioretto
Computer Vision
Inductive Visual Logic for Few-Shot Out-Of-Distribution Adaptation in VLMs
Hung-Jen Chen, Yu-Heng Ho, Ting-Yao Huang et al. (+4 more)
Generative
vision-
language models (VLMs) such as Qwen-VL and LLaVA achieve strong zero-shot performance on tasks overlapping with their pretraining distribution, yet fail on specialized domains where the required discriminative features were never learned, a regime we term distant out-of-distribution (OOD). Standard adaptation methods cannot overcome this representational absence because they operate within the encoder's existing feature space. However, VLMs retain a robust descriptive capacity even when discrimination collapses: a model that cannot classify a medical scan can still articulate its visual patterns. Exploiting this asymmetry, we introduce Inductive Visual Logic (IVL), a training-free framework that constructs classification knowledge from the model's surviving descriptive ability. IVL extracts visual traits from few-shot support images through dual-mode prompting, combining semantic descriptions with primitive visual observations, and organizes them into per-class trait dictionaries. At inference, hierarchical filtering identifies spatially grounded trait evidence for classification. Across multiple distant-OOD
benchmarks, IVL achieves the highest aggregate accuracy under two VLM backbones while producing interpretable, trait-traceable predictions.
Read the full abstract ▾
All authors Hung-Jen Chen, Yu-Heng Ho, Ting-Yao Huang, Po-Hsiang Hsu, Li-Yu Chen, Chun-Yi Lee, Min Sun
Machine Learning
On the Off-Policy Teacher in On-Policy Distillation
Langlin Huang, Hao Liu, Mononito Goswami et al. (+5 more)
On-policy
distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its own policy under dense teacher supervision. However, OPD introduces a fundamental asymmetry: although the sampled trajectories are on-policy for the student, they are off-policy for the teacher. The teacher is typically optimized to continue from prefixes generated by its own policy, but during OPD it must instead supervise prefixes generated by the student. Empirically, we find that its continuation performance degrades as these prefixes grow longer. To address this issue, we propose Student-COnditioned Updates of the Teacher (SCOUT), a co-training framework that adapts the teacher to student-generated prefixes. Alongside standard OPD updates, SCOUT periodically optimizes the teacher's conditional ability using reinforcement learning with verifiable rewards, where the teacher generates continuations from student prefixes and learns from outcome rewards. Controlled experiments show that SCOUT improves the teacher's ability to continue from student-generated prefixes, supporting the intended mechanism of student-conditioned teacher adaptation. Across multiple teacher–student configurations, model scales, and
reasoning domains, SCOUT also consistently improves the effectiveness of on-policy
distillation.
Read the full abstract ▾
All authors Langlin Huang, Hao Liu, Mononito Goswami, Xinyu Li, Prithwish Jana, Nikos Kanakaris, Patrick Blöbaum, Purak Jain
Artificial Intelligence
Beyond Mode Collapse: Generating Diverse Synthetic Expert Conversations via Generative Flow Networks
Sumit Asthana, Michael Ion and Kevyn Collins Thompson
High quality synthetic data is central to post training LLMs for adaptive AI applications that represent the diverse expert strategies and decisions in conversations. Prompting LLMs directly or conditioning them on end use scenarios yields low diversity data that collapses onto dominant modes. We propose a method to generate diverse high quality synthetic data using Generative Flow Networks (GFlowNets). We show that training GFlowNets to generate latent conversation structure using a Gaussian mixture density over key interaction features (e.g., confusion episode dynamics, scaffolding directive balance) enables sampling expert strategies in proportion to their prevalence in the training data. Across two structurally distinct domains, tutoring and emotional support dialogues, our GFlow based synthetic data generation approach offers a better balance of fidelity, mode coverage and authenticity than reinforcement-learning and end to end LLM baselines, without copying training data. Evaluated on three downstream outcome prediction tasks, classifiers trained on synthetic GFlowNet generated conversations provide a stronger training signal than competitive synthesis baselines.
Read the full abstract ▾
Computation and Language
Evaluating Language Model Safety Across Long Adversarial Conversations
Parisa Salmani and Peter R. Lewis
Conversational safety evaluations often test
language models with a single harmful
prompt, even though real-world systems interact with users through long, adaptive conversations. This study examines whether models continue to respond safely when an
adversarial user persists across multiple turns. We evaluate three open-weight, instruction-tuned models on two harmful
prompts across different conversation lengths and random seeds. In each setting, a second
language model acts as a persistent
adversarial user, while a safety classifier labels every response as safe or unsafe. Across all model-
prompt combinations, first-turn safe-response rates ranged from 85% to 100%. By depth 11, they dropped to 38-61%, and by depth 101, to 15-44%. This decline appeared across models and continued well beyond the short interactions typically used in multi-turn safety evaluations. These results provide proof-of-concept evidence that strong single-turn safety does not necessarily persist during sustained
adversarial interaction. They highlight the need for long-horizon evaluations and conversation-level safeguards that account for risk accumulating across turns.
Read the full abstract ▾
Machine Learning
Continual Learning of Dynamical Systems in Recurrent Neural Networks through Recyclable Unit Gating
Sima Hashemi, Daniel Durstewitz and Georgia Koppe
Dynamical Systems Reconstruction (DSR) aims to infer models from observed time series that reproduce a system's qualitative long-term behavior. Continual DSR (cDSR) requires learning new systems while preserving previously learned dynamics, yet even small parameter updates in recurrent models can qualitatively alter their behavior over long autonomous rollouts. We
benchmark established continual learning (CL) methods spanning parameter regularization, replay, and parameter isolation on the fully trainable and interpretable Almost-Linear RNN (AL-RNN). Parameter isolation preserves earlier dynamics most effectively, but excessive task-specific allocations can rapidly exhaust a fixed-size network. We therefore introduce Continually-Recyclable Unit-Gating (CRUG), which conserves capacity through compact allocation and forward transfer. Differentiable gates trained with an $L_0$-based penalty select task-specific units, while unused units are recycled for subsequent tasks. Directed connections allow later tasks to reuse earlier representations without affecting the dynamics of previously committed units. CRUG achieves the strongest reconstruction–capacity trade-off among the tested methods with zero forgetting and reliably learns a heterogeneous sequence of nonlinear and chaotic systems. Furthermore, we show that forward transfer is more pronounced and useful when tasks share similar underlying dynamics. Lastly, we demonstrate that CRUG's advantages extend beyond autonomous cDSR to sequential cognitive tasks.
Read the full abstract ▾
Computation and Language
Halluscoring 2026: The first shared task on llms hallucination detection and answer verification
Aisha Alansari, Abdessalam Bouchekif, Ahmed Hasanaath et al. (+9 more)
We present HalluScoring 2026, a shared task for evaluating
hallucination detection and factual verification in Arabic question answering under challenging generalization settings. Its four subtasks are organized into two tasks. Task~1 evaluates binary
hallucination detection, considering generalization to unseen questions (Subtask 1.1) and responses generated by unseen LLMs (Subtask 1.2). Task 2 extends the evaluation beyond detection by requiring the systems to additionally identify the correct factual answer from six related candidates, covering Islamic knowledge (Subtask 2.1) and general knowledge (Subtask 2.2). The shared task is based on two Arabic
datasets: HalluScore and HalluTruthQA. A total of 13 teams participated in the shared task, ten of which submitted system description papers. The results of Task 1 demonstrate that
hallucination detection remains challenging. On the Task 1 test sets, the top-ranked systems achieved AUC-ROC scores of 0.7717 for Subtask 1.1 (REGLAT) and 0.7670 for Subtask 1.2 (NAMAA). Under assisted evaluation, the highest combined detection and answer-selection scores for Subtasks 2.1 and 2.2 were 0.8824 and 0.8565, respectively.
Read the full abstract ▾
All authors Aisha Alansari, Abdessalam Bouchekif, Ahmed Hasanaath, Salah Eddine Bekhouche, Malak Alkhorasani, Mohammed-En-Nadhir Zighem, Saad Ezzini, Hichem Telli, Hend Al-Khalifa, Muhammad Abdul-Mageed, Hadid Abdenour, Hamzah Luqman
Information Retrieval
TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories
Yu-Shu Chen, Yu-Jung Liang and Pengtao Xie
Long-term
memory lets LLM
agents recall past interactions and remain consistent across sessions, but
memory systems are hard to compare because they often vary in representation, indexing,
retrieval, and evaluation. We present a controlled evaluation framework based on shared 5W-style conversational
memories. Localized graph configurations traverse a common base graph; AdaptiveGraph adds chronological edges and Personalized PageRank
diffusion. We also evaluate BM25 over the same extracted notes and OpenClaw as a raw-input external reference.
Retrieval rankings vary across
memory settings. On LongMemEval-S, AdaptiveGraph is the strongest graph configuration at 0.844 MRR, but BM25 reaches 0.867 and OpenClaw 0.880. On ATANT Core, localized graph traversal outperforms
diffusion and BM25, whereas BM25 leads the stress rounds. Reducing LongMemEval-S within the tested range does not reproduce the ATANT
diffusion penalty, but the smallest tested store remains larger than ATANT Core, so store size cannot be ruled out. The penalty also persists under a permissive content-match criterion. Vocabulary normalization and extraction quality substantially affect graph
retrieval, and missing extraction tags are common among top-five misses.
Retrieval strategies should therefore be evaluated jointly with the
memory setting and against strong lexical baselines.
Read the full abstract ▾
Machine Learning
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
Prithwish Jana, Mononito Goswami, Hao Liu et al. (+9 more)
Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long-horizon performance, yet its combinatorial search space demands substantial human effort that must be repeated as models change. Existing automated methods explore this space narrowly, optimizing only components such as
prompts or skills or becoming trapped by fixed, exploitative search strategies. We introduce MILO (Meta-evolutionary Island Orchestration), a framework that co-evolves
agent harnesses and the strategy used to discover them. MILO combines: (i) hierarchical lineage
memory over island-based trees, using rejected mutations as negative evidence; (ii) per-island mutator
agents that rewrite complete harnesses using global search history and parent-specific feedback; and (iii) an orchestrator that adapts search through lineage grafting and speciation, mutator reassignment and curriculum revision. Across Terminal-Bench 2.1, PaperBench, and DeepSWE, MILO-discovered harnesses outperform eight state-of-the-art harnesses and six search methods using frontier (Opus 4.8) and open-weight (gpt-oss-120b) models. With Opus 4.8, MILO improves resolution over its initial harness by $+12.0\%$, $+28.3\%$, and $+10.3\%$, respectively, compared with best prior-search gains of $+4.5\%$, $+18.3\%$, and $0\%$. On Terminal-Bench 2.1, it achieves $86.1 \pm 2.0\%$, exceeding the official leaderboard's top entry ($83.8 \pm 2.3\%$) while using 26% fewer
tokens than its initial harness. On EinsteinArena open problems, MILO improves best-known upper bounds for Erdős minimum-overlap ($0.3808586 \to 0.3808568$) and the first and third autocorrelation inequalities ($1.50274365 \to 1.50274360$; $1.45081 \to 1.44889$).
Read the full abstract ▾
All authors Prithwish Jana, Mononito Goswami, Hao Liu, Xinyu Li, Langlin Huang, Zhehui Huang, Zhishen Huang, Patrick Blöbaum, Anoop Deoras, Purak Jain, Nikos Kanakaris, Sahika Genc
Machine Learning
Function-Space Transformer with Adaptive Anchors
Guorui Sang and Pedram Rooshenas
Many forms of data, including physical fields,
geometric shapes, and visual signals, are naturally described by functions over continuous domains but are observed through discrete samples. Representing these functions on fixed uniform grids imposes a trade-off between resolving localized variation and increasing computation across the domain. Neural operators address this mismatch by learning mappings between functions, while latent-
attention architectures provide flexible processing of sampled observations. We introduce the Function-Space
Transformer (FST), a framework for learning from functions through a spatially adaptive continuous latent representation. FST stores features at anchors whose locations are predicted from the input observations and recursively refines these anchor features through function-space interactions. This allows the representation to adapt its spatial organization to each input rather than inherit that of the observation grid, while supporting both spatially resolved and finite-dimensional outputs. On PDE solution prediction using PDEBench Burgers and Darcy flow, FST substantially outperforms the Perceiver IO baseline, whose latent representation lacks explicit spatial organization, and is highly competitive with the
Fourier Neural Operator. On ImageNet-1K, FST achieves higher classification accuracy than the
Vision Transformer baseline, with fewer parameters across these comparisons. Ablations further support the benefits of function-space updates and recursive refinement. Together, these results highlight the potential of adaptive continuous representations for both scientific prediction and visual recognition.
Read the full abstract ▾
Computer Vision
TrackFish3D: Self-Supervised 3D Tracking of Schooling Fish from Multi-view Videos
Patt Phurtivilai, Zhiyang Dou, Yifan Wu et al. (+5 more)
Quantifying collective fish behavior requires accurate trajectories, yet multi-view 3D tracking remains challenging due to frequent occlusions, visually similar individuals, and the long-standing scarcity of identity annotations. We present TrackFish3D, a geometry-driven self-supervised framework for dense multi-camera 3D tracking of schooling fish. Instead of relying on appearance-based re-identification or manually annotated identities, TrackFish3D turns calibrated multi-view geometry into supervision: triangulation and reprojection consistency provide pseudo-associations, while a
geometric encoder and global association
transformer learn all-to-all cross-view correspondence within each frame. To make these associations identity-aware, TrackFish3D introduces a self-supervised contrastive objective that separates co-visible individuals in the
embedding space, together with a temporal predictor that preserves identities and bridges short occlusions across frames. The resulting model is trained once on unlabeled footage and applied directly to unseen test
videos, requiring no cross-view identity labels, temporal annotations, 3D ground truth, appearance features, or test-time optimization. On our
benchmark, TrackFish3D improves 3D Multi-Object Tracking Accuracy from 87.7% for the strongest baseline to 95.8%. On the 3D-ZeF zebrafish
benchmark, it achieves 81.1% MOTA, compared with 77.4% for the best
geometric baseline. TrackFish3D also generalizes beyond fish, achieving strong results on real-world bird tracking.
Read the full abstract ▾
All authors Patt Phurtivilai, Zhiyang Dou, Yifan Wu, Kinfung Chu, Yuan Liu, Lei Yang, Wenping Wang, Taku Komura
Artificial Intelligence
Examining Variation in How Guided AI Tutors Resolve Student Impasses
Bakhtawar Ahtisham, Kirk Vanacore, Alessandra Napoli et al. (+5 more)
When a student is stuck, a tutor faces the assistance dilemma: help given too early can hinder productive struggle, while help withheld too long leaves the student in a frustrating, persistent impasse (i.e., wheel spinning). Generative AI tutors increasingly use guardrails restricting answer-giving, yet little is known about how such tutors behave once an impasse persists. We analyze 20,462 student turns from 1,260 authentic sessions with a guided LLM chemistry tutor, identifying 6,630 impasse turns of three major types: conceptual errors, expressed uncertainty, or help-seeking. We then used these impasses to simulate three tutoring conditions to study variation in AI tutor guidance through impasses: baseline, no-direct-answer, and guided tutor. For a sample of 150 impasses,
prompt specificity changed pedagogy: a baseline tutor provided the answer directly in 50.7% of responses, a no-direct-answer tutor asked a follow-up question every time, and the guided tutor responded in a wide variety of ways depending on the context. We then analyzed impasse trajectories in authentic interactions, finding that each additional impasse turn lowered the odds of next-turn recovery by 12.7% (AOR = 0.873, p < .001), and early dropouts were caught in recursive concept elicitation before reaching execution. The benefit of questioning decayed as impasses persisted (scripted question x depth AOR = 0.78; follow-up x depth AOR = 0.83), whereas addressing the student's error grew more beneficial (AOR = 1.14); after a failed scripted question, repeating it was followed by recovery in 28.1% of cases, compared with 39.8% when the tutor addressed the error instead. For learning analytics, these findings identify impasse depth and type as observable, turn-level dialogue signals that analytics can use to trigger graduated, state-sensitive assistance in real time.
Read the full abstract ▾
All authors Bakhtawar Ahtisham, Kirk Vanacore, Alessandra Napoli, Josh Arens, Ksenia Ionova, Clayton Cohn, Shima Salehi, Rene Kizilcec
Software Engineering
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
Chun-Wah Hsu, Kai Gong, Yu Wu et al. (+12 more)
Multi-
agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations are followed faithfully, whereas reality differs. This behavioral gap, combined with differences in underlying system components, prevents clear attribution of observed gains. To this end, we introduce OpenCollab, a multi-
agent coding framework that provides a unified infrastructure for programmable collaboration and controllable runtime. Specifically, OpenCollab unifies organization design, enforces experimental control on a shared runtime, and tracks execution through fine-grained event streams. On this basis, we define Adherence to quantify whether the declared organization is actually realized. Our experiments reveal that
agents collaborate very differently across configurations: changing any single dimension shifts Adherence, from 47.2% to as high as 97.2%. Furthermore, extensive agentic coding
benchmarks show that OpenCollab (Duo) establishes new SOTA performance compared to the mainstream harnesses such as Mini-SWE-
agent, OpenHands, Codex CLI, and Claude Code, showing that a well-designed organization can outperform strong existing harnesses, while OpenCollab's single-
agent configuration uses the fewest
tokens across all evaluated suites. OpenCollab establishes a unified multi-
agent infrastructure for easy programmable collaboration and controlled causal evaluation.
Read the full abstract ▾
All authors Chun-Wah Hsu, Kai Gong, Yu Wu, Xianhe Chen, Mengyang Liu, Jie Li, Hanyu Li, Zhixuan Liu, Naisheng Tang, Jiaying Chi, Ziheng Fan, Xuning He, Xiaokang Yang, Xue Jiang, Yihong Dong
Computer Vision
Learning Semantic Inpainting for Animatable Gaussian Head Avatars
Pilseo Park, Fizza Rubab and Yiying Tong
We present SInGA, a novel method for learning Semantic Inpainting for animatable Gaussian head Avatars from a single image. Existing avatar approaches often rely on multi-view observations and lack effective handling of unobserved regions in single-view settings, limiting their applicability in such scenarios. To address this, we propose a semantic inpainting framework defined in UV space for completing unobserved facial regions. Our key insight lies in the structured
topology of the UV representation, which provides consistent spatial correspondences and enables reliable completion of identity-specific features using the inherent
symmetry cues of human faces. We extract features from observed regions and use them to complete unobserved regions. The completed representation is then used to regress Gaussian attributes, effectively performing Gaussian inpainting. In addition, instead of relying on a single Gaussian at each surface or pixel location, we stack multiple Gaussians to enhance detail. The resulting avatar generalizes across identities without requiring per-identity optimization and can be animated with driving inputs. Experimental results show that our method generates high-quality head avatars with improved completeness and identity preservation, while supporting realistic animation and consistent rendering from unobserved views.
Read the full abstract ▾
Machine Learning
Activation-Conditioned Self-Distillation
Zhexi Lu, Subhajit Chaudhury, Tejaswini Pedapati et al. (+2 more)
On-policy self-
distillation uses a model as its own teacher to provide dense supervision for
reasoning, often through reference-solution conditioning. Providing privileged information does not by itself ensure effective
token-level supervision throughout long responses. We introduce Activation-Conditioned Self-
Distillation (ACSD), which extracts a steering vector by contrasting activations of self-generated trajectories that reach verified correct answers within a generation budget with those of all remaining trajectories. A frozen copy of the base model applies this vector at each prediction position, and the student learns from its next-
token distributions on student-generated prefixes. Outcome verification is used for direction construction and calibration;
distillation requires neither problem-specific reference text nor teacher parameter updates. The distilled student is used alone at inference. On each of five models, ACSD achieves the highest mean accuracy over four mathematical
benchmarks among the evaluated methods. On DeepSeek-R1-0528-Qwen3-8B, mean mathematical accuracy reaches 71.9% and LiveCodeBench v6 pass@12 reaches 70.9%, compared with 69.0% and 66.3% for the reference-conditioned OPSD baseline. Contrasts among correct trajectories also support
distillation, and extracted directions can be reused across mathematical training
datasets. On fixed student trajectories, ACSD maintains more stable late-position logit-update magnitudes than OPSD.
Read the full abstract ▾
All authors Zhexi Lu, Subhajit Chaudhury, Tejaswini Pedapati, Keerthiram Murugesan, Lei Yu
Artificial Intelligence
CARAT: Do Materials LLMs Reason or Recite?
Jiajun Wu, Jian Yang, Zixiang Ni et al. (+2 more)
When a materials LLM answers a question about
crystal structure, does it reason from the structure or copy an answer already printed in its input? Accuracy cannot tell: a structural description often prints the very field it is scored against. CARAT holds question and gold answer fixed across eight matched views, names each structural relation separately in GraphSpace, and adds matched fine-tuning, answer masking, evidence injection, paired inference, and a rule that can withhold claims. First, on the
benchmark's hardest families the grounded view is worth 17.3 points over formula inputs. Second, we turn that scrutiny on ourselves. GraphSpace beats a plain periodic graph by 19.3 points, but that margin is two effects at once: where the plain rendering carries everything the question needs it is 1.96 points, and where it omits those fields entirely, 46.7 points. The headline mostly measures what the baseline lacked, not how evidence is presented. Third, we attack our own
benchmark. A rule that skips the link and reads the list directly answers four of seven hardened families, so we rebuilt it until eleven such shortcuts sat near chance. The frozen model quotes that link yet answers the same when we redirect it, on 95.6% of paired cases: it repeats the relation without using it. After matched supervision it reaches 99.8%, and deleting the link drops it to 23.4%, below the 27.0% the best shortcut reaches: both steps are learnable.
Read the full abstract ▾
All authors Jiajun Wu, Jian Yang, Zixiang Ni, Zhenzhu Li, Bin Chong
Cryptography and Security
Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning
Chaoyu Zhang, Shanghao Shi, Heng Jin et al. (+3 more)
Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly train diagnostic models without exchanging patient records. This
privacy promise, however, is increasingly contested: a malicious or honest-but-curious server can launch model inversion attacks (MIAs) that reconstruct private patient images directly from shared model updates, and recent scalable, closed-form attacks penetrate even secure aggregation at clinically realistic batch sizes. Existing defenses face an unsatisfactory dilemma. Gradient-perturbation methods such as differential
privacy and
pruning trade away the diagnostic accuracy on which clinical reliability depends, while cryptographic protocols add system complexity yet still leave updates exposed to these scalable attacks. We propose Aegis, a principled client-side defense that breaks this dilemma without perturbing patient data or modifying the FL protocol. Our key insight is that the success of every known MIA is fundamentally bounded by the local batch size relative to the model's leakage capacity; once this limit is exceeded, distinct samples collide and reconstructions collapse into indistinguishable mixtures. Aegis turns this universal bottleneck into a defense: each client superimposes onto its real update a masking gradient computed on locally synthesized, task-relevant data, deliberately pushing the effective batch beyond the attack's recovery capacity. We complement the design with theoretical convergence guarantees under standard convex assumptions and evaluate Aegis on MNIST, CIFAR-10, and three MedMNIST modalities (chest X-ray, abdominal CT, colon pathology). Aegis neutralizes three state-of-the-art MIAs while preserving model utility and incurring only modest overhead, offering a practical
privacy primitive for medical FL.
Read the full abstract ▾
All authors Chaoyu Zhang, Shanghao Shi, Heng Jin, Ning Wang, Y. Thomas Hou, Wenjing Lou
Software Engineering
E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch
Hantian Ding, Chloe Bi, Jiacheng Zhu et al. (+5 more)
Coding
agents powered by large
language models (LLMs) are evolving from making localized code changes to developing complete software repositories. However, evaluating repository-scale generation remains challenging: tasks must demand system-level
reasoning while ensuring that all evaluated behaviors are precisely specified and independent of any particular implementation. We introduce E2E-SWE, a
benchmark for evaluating whether coding
agents can build complete, functional software repositories end to end. E2E-SWE contains 186 whole-repository generation tasks spanning 11 programming
languages. Given only a natural-
language specification and an empty workspace, an
agent must implement a complete, installable project that satisfies a comprehensive suite of hidden tests. Each task is constructed by a software engineer in collaboration with an LLM; together, they develop the test suite and a corresponding implementation-independent specification. To ensure that tasks are well specified and practically solvable, we further subject them to an iterative verification process in which autonomous
agents audit and repair task defects using static inspection and failures observed from real model rollouts. Evaluating 13 frontier models, we find substantial variation in end-to-end repository generation ability, with pass@1 ranging from 11.7% to 67.7%, providing strong model differentiation while leaving considerable headroom for future progress. Analysis of
agent trajectories further reveals long, front-loaded
reasoning patterns, highlighting the planning and system-level
reasoning required to construct working codebases from scratch.
Read the full abstract ▾
All authors Hantian Ding, Chloe Bi, Jiacheng Zhu, John Yang, Matt Deitke, Pengcheng Yin, Zijian Wang, Rui Hou
Computation and Language
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Yuhan Guo, Jinming Liu, Liang Xu et al. (+8 more)
Large
language models (LLMs) are increasingly deployed as
agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model methods address this by training
agents to predict future observations, at the cost of additional training and errors that compound when predictions are used for planning. However, for LLM
agents operating in digital environments, much of this world knowledge is already internalized during pretraining, which shifts the problem from acquiring it to eliciting it. We argue that typical post-training provides little pressure for such elicitation, since supervision under a single goal at each visited state inadvertently drives policies to rely on superficial contextual habits. We introduce EVOKE, a post-training method that supplies this pressure through goal diversity at fixed states. Motivated by theory showing that an
agent competent across diverse goals must encode a world model recoverable from its action preferences, EVOKE holds the environment state and interaction history fixed and ranks the same candidate actions under alternative goals, forcing action preferences to change, so that a policy relying on contextual habits or single-goal correlations cannot order them correctly. This implicitly elicits the policy's pretrained world knowledge to inform decisions. We evaluate EVOKE across diverse tasks in three backbones, demonstrating improved task performance, unseen environment generalization, and data efficiency. We further conduct controlled analyses to better understand what drives these gains. These findings offer a new perspective on eliciting internalized world knowledge for transferable action through direct decision supervision.
Read the full abstract ▾
All authors Yuhan Guo, Jinming Liu, Liang Xu, Ziqiang Li, Jianguo Huang, Zhicheng Wang, Hu Zhu, Qiuyu Chen, Yuntao Wei, Xin Jin, Wenjun Zeng
Machine Learning
Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling
Xinyu Li, Mononito Goswami, Hao Liu et al. (+5 more)
Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires deciding how to allocate fresh contexts and what information to carry between them. We call a model's ability to make these decisions contextual
reasoning. Existing approaches largely prescribe these decisions through their harness; we instead shift them to the model. We introduce 1) Hermes, a family of simple, configurable harnesses that progressively varies model control over context allocation and reuse, and 2) Hermes-Learn, a two-stage framework for learning these capabilities. We find that capable models can exploit this flexibility to scale with additional inference-time compute, while smaller open-source models initially struggle to do so. Training with Hermes-Learn closes this gap, inducing adaptive contextual
reasoning strategies that vary with both the problem and the progress of
reasoning. These gains generalize across
benchmarks and models, extrapolate beyond the inference-time compute seen during training, and transfer to complementary test-time scaling methods beyond Hermes.
Read the full abstract ▾
All authors Xinyu Li, Mononito Goswami, Hao Liu, Nikos Kanakaris, Langlin Huang, Prithwish Jana, Patrick Blöbaum, Purak Jain
Computer Vision
ExploreNet: Learning Where to Explore in Diffusion GRPO
Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov et al. (+1 more)
Group-relative RL methods such as Flow-GRPO post-train image generators by exploring with isotropic Gaussian noise added at every denoising step. This noise decides which rollouts the model learns from, yet it perturbs every channel and spatial position of the latent equally. In this paper, we instead show that latent elements differ in how much they change the generated image, so exploration should adapt to these differences. We introduce EXPLORENET to learn an adaptive exploration distribution. EXPLORENET is a policy that predicts a noise scale for every latent element from the current latent, the denoising step, and the
prompt, before any reward is observed; it is trained on the reward spread of each rollout group and discarded after training, leaving inference unchanged. On Stable
Diffusion 3.5 Medium, EXPLORENET improves held-out GenEval2 by 14% over Flow-GRPO, transfers to two independent compositional
benchmarks and five preference and image-quality models, and reaches a 67.2% human preference win-rate. Overall, across our group-relative
diffusion RL experiments, we find that exploration is learnable, the shape of the exploration distribution outweighs its magnitude, and rollout quality is more effective than rollout quantity.
Read the full abstract ▾
All authors Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov, Luke Zettlemoyer
Multiagent Systems
Absorbing State Phase Transitions in Multi-Agent Search
Wenwen Zheng, Yuzhe Yang, Helen Qu et al. (+2 more)
Nontrivial dynamics can emerge in large
language model (LLM)-based multi-
agent systems, and preliminary evidence exists that formalisms from statistical mechanics can be effective at modeling and predicting such behaviors. In parallel, designing multi-
agent communication
topology for optimal task-solving is an active research question. In this paper, we focus on predicting the success of multi-
agent search tasks using the formalism of absorbing state phase transitions. We first taxonomize search tasks into four types, informed by classical results in combinatorial search. We then theoretically derive a critical communication degree $d_c$, the minimum number of
agents each
agent can communicate with, above which incorrect hypotheses do not proliferate uncontrollably and the search enters the solved state. Finally, we evaluate frontier LLM-based multi-
agent systems on real-world search and discovery tasks, software configuration debugging and physical mechanism discovery, and find that agreement with theory is mixed. LLM
agents may not communicate with their neighbors and can develop strategies that are individually beneficial but limits the benefits of collaboration.
Read the full abstract ▾
All authors Wenwen Zheng, Yuzhe Yang, Helen Qu, Xin Eric Wang, Haewon Jeong