Machine Learning
Does Learning Protein Folding Generalize to Broader Reasoning?
Yong Liu, Zhanpeng Shi, Yizhou Dang et al. (+4 more)
Large
language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them.
Protein folding is a natural testbed, because one solved structure yields thousands of exactly checkable spatial and topological statements. We ask: can learning to fold
proteins teach general models reusable
reasoning capabilities? To answer this, we build FoldingCorpus, a
protein-derived question-answer
dataset, and Fold2Reason, a recipe that post-trains on it through two complementary signals: discrete structural answers predicted via the model's native
language head, and continuous 3D geometry decoded from the same shared representations. On FoldBench, Fold2Reason achieves structure prediction scores 2.7 to 3.5 times those of Qwen3.5-9B. Beyond
protein structure prediction, it improves performance on all 10
benchmarks spanning spatial, graph, scientific, and general
reasoning, raising macro-average accuracy from 45.09% to 48.33% (+3.23 pp), with positive gains on all 10
benchmarks, while matched controls built from random, synthetic, and shuffled structure yield substantially smaller or negative gains. Our work shows that non-linguistic, structure-dense scientific data can systematically improve broad
reasoning in
language models, making a solved scientific problem a practical source of post-training supervision.
Read the full abstract ▾
All authors Yong Liu, Zhanpeng Shi, Yizhou Dang, Zhongyue Zhang, Xiaoliang Shi, Zhijian Wei, Shuangjia Zheng
Machine Learning
On Parameters of Nonlinear Scalar Dynamics from Video: Invariants, Calibration, and Identifiability
Wenjie Wang, Yuanyuan Wang, Zixiang Jiang et al. (+2 more)
Physical parameter estimation from
video aims to recover the parameters of a known family of governing dynamical equations from pixel observations. Existing identifiability theory for this setting has focused on linear time-invariant (LTI) second-order systems, leaving open what can be identified for nonlinear scalar dynamics. We develop an identifiability theory for nonlinear scalar second-order ODEs, organized by how their velocity dependence interacts with changes of the learned state coordinate. Under a shared non-collapsed state map and explicit same-state velocity-coverage conditions, we show that parameter identifiability depends on the ODE family: some parameters are uniquely identifiable, while in other families only invariant parameter combinations are identifiable or external physical calibration is required. For laws that are at most linear in velocity, compatibility forces affine coordinate
alignment, yielding explicit parameter relations, invariants, and calibration conditions. This affine conclusion extends to broader finite velocity-feature families when coordinate
curvature can be separated from the declared velocity dependence. For families admitting a squared-velocity term, nonlinear coordinate ambiguity can remain; a law-derived normalization instead enables affine comparison between canonical laws. Experiments on synthetic systems and real pendulum and free-fall
videos support the predicted parameter relations, coverage effects, and calibration requirements.
Read the full abstract ▾
All authors Wenjie Wang, Yuanyuan Wang, Zixiang Jiang, Shaoan Xie, Mingming Gong
Machine Learning
GeoNest: Learning to Select Failure-Aware Neighborhoods for the Irregular Knapsack Problem in a Circular Container
Zhongman Du, Huiming Zhang, Linlin Yang et al. (+2 more)
The two-dimensional irregular knapsack problem in a fixed circular container is an important combinatorial optimization problem for maximizing material utilization in manufacturing. Conventional
geometric packing solvers can produce tightly packed layouts, yet they often partition the residual space into isolated small pockets that cannot fit valuable unplaced polygons. To overcome this late-stage packing bottleneck, we propose a failure-aware large neighborhood search framework named GeoNest, driven by a graph policy trained via reinforcement learning. Specifically, we first construct neighborhoods by pairing failed target polygons with residual pockets. We then use explanatory poses to identify the placed polygons that block candidate insertions. These diagnosed blocking relations define bounded, fixed-item repair subproblems for the underlying
geometric solver. Finally, the graph policy selects the most promising subproblem for execution. For evaluation, we introduce CircleNest-Bench, a
benchmark comprising 2,391 load-controlled instances from four contour sources, including a held-out industrial CAD source. Experimental results demonstrate that, under the same total time budget, GeoNest improves mean utilization over a state-of-the-art standalone packing solver by about 0.9% on average across the three main test sets and by about 0.6% on the held-out industrial set.
Read the full abstract ▾
All authors Zhongman Du, Huiming Zhang, Linlin Yang, Sheng Xu, Baochang Zhang
Machine Learning
Optimal Design for Active Preference Learning with Biased LLM Judges
Zhongman Du, Huiming Zhang, Haodong Zhu et al. (+1 more)
Learning from human preferences is central to large
language model (LLM)
alignment, but human preference annotation is costly. Active preference learning reduces this cost by selecting informative comparisons, and LLM judges can provide additional scalable feedback. However, the preferences of the judges may deviate from those of the target human population. Even after calibration on trusted reference data, active acquisition can shift the comparison distribution and expose residual judge bias. We therefore incorporate judge deviations into the acquisition design rather than relying on a separate calibration stage. Under joint estimation, comparisons that appear highly informative about the reward may also reflect judge bias and therefore provide less information about human preferences. To address this issue, we propose Nuisance-Adjusted Optimal Design (NAOD), a comparison-selection strategy that prioritizes policy-relevant target information after nuisance adjustment and uses the Frank-Wolfe
algorithm for optimization. Theoretically, we establish a sharp conditional local asymptotic minimax lower bound on policy risk and construct an
estimator that attains it. We further characterize the finite-sample cost of learning the nuisance representation and show that representation error can reverse an oracle design advantage. Finally, we validate these predictions experimentally and evaluate NAOD on Chatbot Arena data across 17 judges, 15 budget configurations, and 15 random cluster-level splits. NAOD reduces the mean regret of proxy policy by 29.1% relative to a matched target-information design, outperforms existing methods, and improves human-preference prediction on held-out data.
Read the full abstract ▾
All authors Zhongman Du, Huiming Zhang, Haodong Zhu, Baochang Zhang
Machine Learning
Mitigating the Length-Scaling Tax with Online Distillation
Xu Wan, Wenyue Xu, Shengjie Zhao et al. (+1 more)
Length scaling during reinforcement-learning (RL) post-training is often viewed as a sign of improved
reasoning ability, especially on difficult problems, but may also make responses to already-solved problems unnecessarily verbose. We quantify this side effect as the length-scaling tax (LST): excess response length on already-solved queries without a commensurate accuracy gain. To mitigate LST, we propose Length Self-
Distillation (LSD), which routes solved
prompts to on-policy
distillation and retains the original RL objective for unsolved
prompts. LSD uses an exponential moving average of the online policy as its teacher, requiring no external model. We find that LSD achieves comparable or better performance than RL across multiple variants, while substantially curbing response-length growth on easy queries. LSD reduces LST from 19.0% to -3.7% on single-turn
reasoning and from 31.4% to 13.7% on multi-turn agentic tasks, demonstrating that LSD effectively preserves concise response patterns on easy queries while supporting efficient exploration on difficult queries during RL post-training.
Read the full abstract ▾
All authors Xu Wan, Wenyue Xu, Shengjie Zhao, Mingyang Sun
Machine Learning
Visualizing Distribution Coverage in Generative Diffusion Models
Yifei Wang, Xiaoyu Wu, Tsu-Jui Fu et al. (+4 more)
Diffusion distillation is widely adopted to accelerate sampling, and the resulting few-step models are broadly believed to match or even surpass their multi-step teachers in generation. However, standard evaluations such as GenEval2 typically draw only one sample per
prompt, so improved scores may fail to reveal losses in distribution coverage. We therefore revisit whether distilled models truly match their teachers beyond single-draw performance using \textbf{pass@$\mathbf{k}$}, which measures the probability that at least one of $k$ independent samples satisfies a quality criterion. At $k{=}1$, pass@$k$ reduces to standard single-draw evaluation. As $k$ grows, the curve reveals whether additional draws find genuinely different successes or merely revisit the same modes, directly exposing how broadly a model covers the space of valid outputs. We first show that classifier-free guidance (CFG), whose quality–coverage tradeoff is well established, is the clearest case: higher guidance improves pass@$1$, but its advantage shrinks and reverses at larger $k$. Applying pass@$k$ to few-step distilled models, we find the same tradeoff splits along training objectives: distribution-matching objectives concentrate the student's output distribution, boosting early-hit rates while eroding large-budget coverage, whereas consistency and trajectory-based objectives better preserve the teacher's coverage even at large $k$. We further show that this tradeoff extends to few-step causal
video generation. Our findings reveal a previously overlooked cost of
diffusion distillation: across both image and
video generation, the choice of training objective fundamentally determines whether a few-step model inherits its teacher's distribution coverage or trades it away for single-draw quality.
Read the full abstract ▾
All authors Yifei Wang, Xiaoyu Wu, Tsu-Jui Fu, Chen Chen, Liang-Chieh Chen, Zhe Gan, Chen Wei
Machine Learning · Cross-listed from cs.CL
Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis
Xia Hu, Brian Potetz, Chun-Ta Lu et al. (+6 more)
End-to-end accuracy on compositional tasks records how often MLLMs fail, but cannot distinguish whether a failure reflects an intrinsic deficit in the targeted capability or a cascading error from an upstream prerequisite. We propose a causal decomposition framework that isolates these two failure modes through controlled interventions on the prerequisite dependencies of each task. Our capability metrics (NC, IC, RC) score each task under unassisted, correct, or incorrect prerequisites to diagnose where failures arise; contribution metrics (N-Score, S-Score), adapted from probabilities of causation, quantify each prerequisite's necessity and sufficiency to determine why. We instantiate the framework in CADET, a diagnostic
benchmark of 10 composite tasks decomposed into 46 unit tasks with over 33,000 human-annotated questions spanning perception, spatial, temporal, and cognitive categories. Diagnosing frontier MLLMs with our framework uncovers systematic patterns that end-to-end accuracy obscures. Capability-wise, supplying correct prerequisites eliminates 54% of errors on cognitive tasks, lifting them from weakest to above spatial and temporal. Prerequisite-wise, causal contributions are concentrated in a few critical prerequisites, and supplying the single most important one alone captures 84% of the gain from supplying all prerequisites.
Read the full abstract ▾
All authors Xia Hu, Brian Potetz, Chun-Ta Lu, Huanfen Yao, Leonidas Guibas, Zhicheng Wang, Howard Zhou, Pengfei Xing, Andrew Gallagher
Machine Learning
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
Maoqi Liu, Junwei He, Bowen Zhang et al. (+5 more)
Rubric-based reinforcement learning (Rubric-RL) trains
language models where no verifier exists. A judge checks each criterion of a rubric, and the verdicts are aggregated into a reward, most often by a weighted sum. We show that this additive aggregation is the weak point. Under a sum, criteria compensate for one another: a policy that misses the one decision that matters can buy the points back with advice nobody asked for. On clinical consultation, such a policy scores higher and answers worse. Rubric coverage rises while appropriateness on held-out physician criteria falls below the untrained model. The medical criteria are not to blame. Grouped so that they must hold together, the same criteria, unchanged to the word, recover a third of the loss; shorter answers recover almost none. We therefore propose Protocol-level Rubrics (ProRubric), which keeps what the criteria ask for and changes how they are aggregated. It groups a checklist into a few protocol-level dimensions. A dimension counts only when all of its criteria hold and its failure clause does not fire. The grouping is done once, offline, and leaves the optimizer unchanged. ProRubric raises appropriateness by 10.8 points without losing coverage and has the best seven-
benchmark average at both scales. Reward validity is set not only by what a rubric verifies, but by how it aggregates. Code is available at https://github.com/Estrellajer/ProRubric
Read the full abstract ▾
All authors Maoqi Liu, Junwei He, Bowen Zhang, Feiran Li, Wentao Ma, Rongyi Lin, Shuhan Zhong, Quan Fang
Machine Learning · Cross-listed from stat.CO
Learn-Then-Differentiate Gradient Estimation
Nifei Lin, Qingkai Zhang and L. Jeff Hong
Learn-then-differentiate (LTD) estimates gradients by fitting a model to simulation outputs and differentiating it. We develop a unified framework explaining what LTD differentiates and how accurately it estimates gradients. For models with a weighted representation, LTD differentiates a learned representation of the underlying probability measure. We then show how accuracy guarantees for fitted models translate into guarantees for gradients and higher-order derivatives, with rates approaching the standard Monte Carlo rate under suitable smoothness conditions. The framework recovers established results for kernel regression, local
polynomial regression, and kernel ridge regression, and yields further guarantees for multiple kernel learning and smooth neural networks. These results provide a common foundation for understanding and analyzing LTD across learning methods.
Read the full abstract ▾
Machine Learning
scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation Learning
Yunhak Oh, Yoonho Lee, Junseok Lee et al. (+9 more)
Single-
cell RNA-seq representation learning is fundamentally label-free:
cell identities, states, and contexts are not fixed training targets, so what constitutes signal or nuisance is analysis-dependent. A single representation must therefore preserve biological identity and state, remain robust to nuisance context, and retain the gene-level variation needed for expression analysis, three demands we call the representation trilemma. To tackle this problem, we introduce scTrilemma, a latent-bottleneck VAE that routes expression-derived variation to the
embedding, the decoder, or the prior rather than forcing all of it through one
embedding. It gates gene
tokens by expression, routes the
cell representation through the decoder, and conditions the prior on unlabeled pseudo-bulk context, under a single reconstruction objective and without target annotations or auxiliary representation losses. In release-based zero-shot evaluation on successive CZ CELLxGENE Census releases, scTrilemma leads all three demands at once and preserves biological-state, differential-expression, and pathway structure across multiple disease settings. Latent interventions further show that context can be removed at almost no cost to the other demands, leaving identity against fidelity as the remaining tension. Code is publicly available at https://github.com/yunhak0/scTrilemma.
Read the full abstract ▾
All authors Yunhak Oh, Yoonho Lee, Junseok Lee, Namkyeong Lee, Sang-Yeon Hwang, Yinhua Piao, Hyomin Kim, Seonghwan Kim, Jaechang Lim, Woo Youn Kim, Sungsoo Ahn, Chanyoung Park
Machine Learning · Cross-listed from quant-ph
Average-and Last-Iterate Lower Bounds for Optimistic Matrix Mirror-Prox in Quantum Zero-Sum Games
Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis and Pucheng Xiong
Optimistic
matrix mirror-prox (OMMP) computes $\epsilon$-approximate Nash
equilibria in
quantum zero-sum games with an $O(1/\varepsilon)$ average-iterate guarantee [arXiv:2311.10859]. We investigate whether this dependence on accuracy is tight and whether
geometric last-iterate convergence can be guaranteed. We study these questions through explicit games with one
qubit per player. First, we prove an $\Omega(1/\varepsilon)$ lower bound for the uniform-average output that includes the maximally mixed initial state, independently of the regularizer and step size. Second, we construct a fixed game on which optimistic gradient descent-ascent (OGDA), initialized at the maximally mixed state, has last-iterate Frobenius distance to
equilibrium $\Theta(1/t)$ and duality gap $\Theta(1/t^3)$ for every sufficiently small fixed step size. A separate fixed game exhibits arbitrarily long delays in reducing the initial error by a constant factor across a family of initial states. Finally, we give a fixed game with a unique, strictly complementary
equilibrium on which optimistic
matrix multiplicative weights updates (OMMWU) converge only polynomially from the maximally mixed state for every fixed positive step size. The last-iterate Frobenius distance and
quantum relative
entropy from the
equilibrium to the iterates decay as $\Theta(1/t)$, while the duality gap decays as $\Theta(1/t^2)$.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DS
Optimal VC Dimension of Contrastive Learning with Margin
Dionysis Arvanitakis, Vaggos Chatziafratis, Yiyuan Luo et al. (+1 more)
Contrastive learning is a successful paradigm for learning $d$-dimensional
geometric representations from a collection of “anchor–positive–negative” triplets $(i,j^{+},k^{-})$, indicating that “item $i$ is closer to $j$ than to $k$.” Despite its success, understanding why contrastive learning leads to representations of high generalization quality—beyond the often pessimistic predictions from PAC-learning—remains a central question. Recently, \citet*{alon2024optimal} proved that, for PAC-learning $d$-dimensional Euclidean representations of $n$-point
datasets, $\Theta(\min(nd, n^2))$ triplets are necessary and sufficient, while they posed as an open question whether their VC dimension bounds for the more realistic setting of contrastive learning with a margin can be improved. For a margin parameter $\alpha >0$, a triplet $(i,j^{+},k^{-})_{\alpha}$ is satisfied by the
embedding $\phi:[n]\rightarrow \mathbb{R}^{d}$, if $\|\phi(i)-\phi(k)\|_2>(1+\alpha)\cdot\|\phi(i)-\phi(j)\|_2$. In this work, we resolve their question by proving that the VC dimension of contrastive learning under any margin $\alpha\in(0,1)$ is in fact $O(n/\alpha^2)$, improving on the previous bound of $O(n\log(n)/\alpha^2)$. We also establish that the bounds are optimal up to constant factors, by providing a matching lower bound of $\Omega(\frac{n}{\alpha^2})$ (the previously known lower bound was $\Omega(\frac{n}{\alpha})$), for $\alpha\geq \max(n^{-1/2},d^{-1/2})$.
Read the full abstract ▾
All authors Dionysis Arvanitakis, Vaggos Chatziafratis, Yiyuan Luo, Konstantin Makarychev
Machine Learning
ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learning
Sungmin Kang, Zhengzhong Tu and Sunwoo Lee
Federated continual learning must integrate new tasks over time without losing earlier-task knowledge. Most existing methods attach an anti-forgetting mechanism to the client-trained, server-aggregated loop of
federated learning, which holds back new learning to preserve earlier knowledge and burdens resource-constrained clients. We propose ReSCENE, which structurally mitigates catastrophic forgetting by having each client upload a small condensed surrogate of its local data while the server keeps the surrogates of past tasks and trains the global model on them together with the current task surrogates. For efficient server
memory, we introduce temporal herding, which selects the more recent surrogates from the pool accumulated over a task into a compressed buffer. Our study provides a theoretical analysis showing that this buffer can represent the original task data more closely than full accumulation of all surrogates. Across CIFAR-10, CIFAR-100, and TinyImageNet, ReSCENE achieves the strongest accuracy over seven baselines, by up to $31.1$ points of average accuracy, while requiring as little as $0.11\times$ of the client computation and up to $179\times$ less upload than the model-update baselines. ReSCENE further demonstrates its effectiveness when scaled to larger client populations and larger models while remaining efficient, which makes it a practical method for
federated continual learning.
Read the full abstract ▾
Machine Learning
SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs
Fahao Chen, Linkang Du, Jinhao Zhou et al. (+2 more)
Sparse
attention is widely used to accelerate long-context inference in modern large
language models (LLMs), but its input-dependent execution behavior introduces previously unexplored
privacy risks. We identify a new GPU micro-architectural side channel, termed Sparsity-Induced
Memory Access (SIMA), which arises from secret-dependent key-value cache access patterns induced by sparse
attention. Based on this observation, we present SparLeak, a phase-aware side-channel attack that extracts SIMA traces during LLM inference and enables two practical
privacy extractions: query attribute inference from prefill-phase traces and autoregressive response reconstruction from decoding-phase traces. By reconstructing approximate
token-level sparsity profiles from page-level observations and applying profiling-based learning, SparLeak accurately recovers sensitive information, including user-query attributes and private LLM response content. Extensive evaluation across three LLM architectures, three sparse
attention mechanisms, and three
privacy-sensitive
datasets shows that SparLeak achieves average attack success rates of 90.9% for attribute inference and 87.3% for response reconstruction under real-world LLM serving settings, highlighting the significance to account for SIMA leakage when deploying sparse-
attention-based LLM systems. We provide anonymized SIMA traces, trained attack models, evaluation scripts, and documentation as artifacts at https://anonymous.4open.science/r/Janus_artifacts/.
Read the full abstract ▾
All authors Fahao Chen, Linkang Du, Jinhao Zhou, Peng Li, Zhou Su
Machine Learning
Learning Chaos Without Seeing Chaos: Extrapolation of Global Dynamics in Autoregressive Transformers
Yilun Liu, Yi Zhang, Ganyu Wu et al. (+5 more)
Autoregressive models are trained to predict a system's behavior one step at a time, and recursive generation allows the learned dynamics to unfold over long horizons. To what extent can such dynamics learned from local observations recover broader organization of an underlying system that was only partially observed during training? Here we study small autoregressive
transformers trained from scratch on trajectories sampled from restricted parameter regimes of several non-linear dynamical systems, including logistic and sine maps, the Lorenz system, and the generalized Hopf system, with control parameters and state trajectories represented as sequences of continuous
tokens. Under closed-loop evaluation at parameters far outside the training distribution, the models can recover self-similar period-doubling cascades, chaotic dynamics, and attractor structures with remarkable visual and numerical fidelity. For the logistic map, a
transformer reproduces successive period doublings up to period 128, yielding a finite-order scaling ratio of 4.6687, matching the Feigenbaum constant to within $5\times10^{-4}$. We further investigate how these structures emerge over the course of training, and reveal with causal interventions how control-parameter information is processed through
attention into state prediction and shapes the resulting closed-loop dynamics. These results suggest that a surprisingly narrow window into a system's local behavior may suffice for autoregressive
transformers to generalize to its unseen global dynamical organization.
Read the full abstract ▾
All authors Yilun Liu, Yi Zhang, Ganyu Wu, Sikuan Yan, Mengyue Wang, Alois Knoll, Volker Tresp, Yunpu Ma
Machine Learning · Cross-listed from cs.CL
Can Terminal Agents Trust Their Own Verification? Diagnosing and Improving Self-Verification
Yingfeng Luo, Shaowei Wei, Daixin Wang et al. (+7 more)
Terminal
agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments. Yet how trustworthy such self-verification is remains poorly understood. To investigate this question systematically, we introduce a diagnostic framework that identifies the first complete solution in each trajectory, determines whether it is objectively correct, and uses this ground truth to quantify the
agent's subsequent verification and recovery behavior. Applying it to ten terminal
agents on TerminalBench2.1, we find that verification is nearly universal after a complete candidate is formed, yet only 61.43% of incorrect candidates are detected and only 49.36% of detected errors are successfully repaired. These results show that the main weakness in self-verification lies not in initiating verification, but in detecting and repairing errors. Motivated by these findings, we propose Student-Conditioned Verification
Distillation (SCVD), which lets the student first produce a candidate solution and distills a stronger teacher's subsequent verification and recovery from the same interaction context. Across three Qwen3.5 backbones, SCVD improves Pass@1 on TerminalBench2.1 by 9.74–16.85 percentage points over the corresponding base models and by 4.49–8.61 points over the standard full-trajectory
distillation, while avoiding the pronounced out-of-distribution degradation of full-trajectory
distillation on SWE-bench Verified.
Read the full abstract ▾
All authors Yingfeng Luo, Shaowei Wei, Daixin Wang, Dingyang Lin, Kaiyan Chang, Weiqiao Shan, Tong Zheng, Zhiqiang Zhang, Jingbo Zhu, Tong Xiao
Machine Learning · Cross-listed from cs.CV
DCM-SAM: Defect-Conditioned Mixture of LoRA Experts for NPU-Deployed AM Defect Segmentation
Md Mushfiqur Rahaman, Md Mahedi Hasan, Imtiaz Ahmed et al. (+1 more)
Metal additive manufacturing parts are inspected by X-ray computed
tomography, where labelled data is scarce, the pores and inclusions that matter span a few pixels, and inspection must happen at the machine. We present DCM-SAM, a defect-conditioned adaptive mixture of LoRA experts: one frozen Segment Anything backbone carries a separate Conv-LoRA expert bank and mask decoder per defect class, each trained in its own pass, without
prompts, on synthetic slices alone, updating only 4.4% of the parameters. On
benchmarks that XCT-SAM reports, DCM-SAM improves on every baseline for both classes from a ViT-B backbone against their ViT-H, and reaches 64.2% pore IoU on real NIST scans having seen no real images during training. Deployment then exposes what adaptation work rarely measures: on a Qualcomm Hexagon NPU, ViT-H and ViT-L compile yet cannot allocate at 1024x1024 image resolution, since activations rather than weights exceed the device ceiling, and quantizing weights does not help. ViT-B alone runs, but the adapted encoder then fails to allocate where the stock one succeeds, until a numerically identical rewrite of the
attention lets the complete DCM-SAM run in FP16 at 1024x1024, with no operator falling back to the CPU, masks within 0.01% of pixels of the FP32 reference. Code: https://github.com/MushfiqShovon/DCM-SAM.
Read the full abstract ▾
All authors Md Mushfiqur Rahaman, Md Mahedi Hasan, Imtiaz Ahmed, Srinjoy Das
Machine Learning
Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained Problems
Woosang Jeon, Jaeyeon Kim, Sham Kakade et al. (+6 more)
Next-
token prediction has driven remarkable progress in large
language models, yet a growing body of evidence suggests that they can struggle on problems governed by complex global constraints. In this work, we focus on this regime and ask whether some of these limitations arise from the inference interface induced by next-
token prediction itself. We study this question through blackboard intelligence: an inference-time perspective in which a model works on a fixed, revisable canvas and searches over candidate solution states rather than committing to a causal, left-to-right trajectory. We instantiate this idea with
diffusion language models, whose any-order prediction interface naturally exposes predictions over partially filled solution states. Our key observation is that mean confidence, a simple model-internal quantity available from the standard masked
diffusion objective, provides a useful proxy for global coherence and can guide inference-time search and revision. Empirically, across ZebraLogic, Nurse Rostering, and Job-Shop Scheduling, Blackboard consistently improves inference while holding the fine-tuned LLaDA-8B-Instruct checkpoint fixed and substantially outperforms same-scale autoregressive baselines, reaching 90.4% accuracy on ZebraLogic-Hard, 76.4% exact feasibility on Nurse Rostering, and 80.2% optimality on JSSP. Stronger autoregressive search and refinement also fail to close the gap on ZebraLogic-Hard, while Blackboard surpasses tested frontier LLMs there and on JSSP despite their substantially greater scale and strong test-time
reasoning. We open-source our codebase at https://github.com/jwoosang1/blackboard-intelligence.
Read the full abstract ▾
All authors Woosang Jeon, Jaeyeon Kim, Sham Kakade, Yilun Du, Amrit Singh Bedi, Arun Kumar Chithanar, Chul Lee, Taehyeong Kim, Sitan Chen
Machine Learning
Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
Huaiyu Fu, Heng Cao, Hao Wang et al. (+2 more)
LLM
agents often admit multiple high-quality solutions to the same task, differing in
reasoning structure, tool-use pattern, or interaction trajectory. Yet existing notions of diversity in LLM post-training are mostly implicit, arising from general stochasticity and regularization mechanisms rather than explicitly targeting task-relevant behavioral variation. While such implicit diversity can be useful, it does not directly specify which forms of behavioral variation should be encouraged for a given task. In this work, we study explicit trajectory diversity in RL-based post-training for LLMs. Our key idea is to define diversity through user-specified, task-specific trajectory descriptors, which map each sampled trajectory to an interpretable behavioral representation, and then measure diversity as a set-level functional over the resulting descriptor
matrix. Building on this formulation, we introduce Trajectory-guided Joint Policy Optimization(TJPO), a single-policy framework that optimizes explicit diversity over sampled trajectory groups, avoiding the need for population-based policy training, and instantiate it within group-based policy optimization through trajectory-level learning signals. This design makes the diversity objective both interpretable and controllable. Experiments on Sokoban and ALFWorld show that TJPO improves task-specific trajectory diversity while maintaining competitive task performance. Descriptor and trajectory analyses show that the learned variation follows the specified behavioral dimensions and includes distinct successful strategies. Extra experiment results suggest that explicitly shaping trajectory diversity can help LLM
agents satisfy user requirements and remain effective when task conditions change.
Read the full abstract ▾
All authors Huaiyu Fu, Heng Cao, Hao Wang, Jian Ya, Tao Chen
Machine Learning
Evaluating Persistent Calibration under Evolving Model Knowledge
Victor Wang, Thomas Hofweber, Mohit Bansal et al. (+1 more)
As AI systems move from static repositories to
agents that are capable of continual adaptation and learning, maintaining their trustworthiness means equipping the models backing them with the ability to produce confidence estimates that dynamically reflect their changing skills and knowledge. We introduce the problem of persistent calibration, which requires a confidence
estimator to faithfully reflect the knowledge contained in a model as that knowledge changes, without recurring supervision. We operationalize this by examining persistent calibration across checkpoints of open models, asking whether confidence
estimators trained on earlier checkpoints can generalize to later ones. Specifically, we aim to shed light on whether confidence is dependent on knowledge, a question with implications for the reliability of confidence estimates. To measure this relationship, we define and evaluate calibration on knowledge contrast sets: subsets containing questions that one checkpoint answers correctly and another checkpoint answers incorrectly, reflecting a change in knowledge. We show that both inference-time and fine-tuning methods fall short on contrast-set calibration compared to oracle methods trained on future checkpoints, even for methods that are well-calibrated on the full
dataset. We provide evidence for the hypothesis that persistent calibration is challenging because there is a vast space of possible confidence functions that are well-calibrated on a given checkpoint, out of which only some rely on meta-knowledge features that would generalize to other checkpoints. Towards improving contrast-set calibration, we show that multi-checkpoint training helps, suggesting an avenue for identifying confidence features that remain robust across changing knowledge.
Read the full abstract ▾
All authors Victor Wang, Thomas Hofweber, Mohit Bansal, Elias Stengel-Eskin
Machine Learning · Cross-listed from cs.CL
Recovering Off-Policy Supervision for Speculative Decoding
Jungseob Lee, Chanjun Park, Sugyeong Eo et al. (+1 more)
Block drafters for speculative decoding are commonly trained on corpora written by external models, where a single off-policy
token invalidates supervision for all subsequent slots in a block. Existing approaches discard these divergent slots, resulting in severe supervision loss. To resolve this problem while preserving the training corpus, we propose a rollout-based training framework that recovers full supervision through two complementary components. The first component, Anchor-Label Relabelling (ALR), replaces corpus labels with distributions from greedy target rollouts, restoring valid supervision across all predicted slots. The second component, In-Rollout Anchors (IRA), places draft blocks directly inside these rollouts to expose the drafter to target-generated context, reusing precomputed rollout features at no additional target cost. Across fixed
vision-
language and text corpora, our framework increases greedy accepted length by up to 36.5% over DFlash and consistently outperforms erasing baselines. Notably, a single epoch of our method surpasses the best erase schedules. After three epochs, it matches the acceptance length of training on target-regenerated responses. These results show that our framework provides an effective and compute-efficient approach for training speculative drafters on fixed corpora without modifying the original text. Code is available at https://github.com/js-lee-AI/ALR-IRA.
Read the full abstract ▾
All authors Jungseob Lee, Chanjun Park, Sugyeong Eo, Hyeonseok Moon
Machine Learning · Cross-listed from cs.CL
Training LLM Judges from Language Feedback via Position-Selective Self-Distillation
Ilgee Hong, Changlong Yu, Zhenghao Xu et al. (+5 more)
We study training LLM judges from natural
language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation criteria the judge invokes and how it weighs them. The dominant approach, outcome-supervised RL (e.g., GRPO), credits every
token in the rollout with a single scalar determined only by the accuracy of the final verdict, providing no separate credit at the criterion-choice
tokens and ignoring the rich
language feedback (e.g., preference rationales) that naturally accompanies preference labels. Self-
Distillation (SD) is one natural way to use this
language feedback: the same model, conditioned on this feedback, acts as a teacher providing dense, position-level supervision. However, not all positions carry equally useful signal. Using the per-position
entropy shift between teacher and student, we identify two regimes: context sharpening, where the teacher concentrates probability on a particular feedback-aligned criterion expression, and context spreading, where the teacher distributes probability across multiple feedback-aligned alternatives. We interpret these patterns as follows: sharpening encourages memorization of a particular criterion expression, whereas spreading promotes semantic understanding by preserving these alternatives. Motivated by this asymmetry, we introduce position masking based on the
entropy shift that retains the lower tail of the
entropy-shift distribution. Experiments show that masking higher-
entropy-shift positions improves out-of-distribution generalization over naive SD. The resulting self-distilled judges outperform judges trained with outcome-supervised RL by 2-9 percentage points on the evaluated subjective subcategories, while remaining competitive on objective ones.
Read the full abstract ▾
All authors Ilgee Hong, Changlong Yu, Zhenghao Xu, Xin Liu, Yuwei Zhang, Qin Lu, Bing Yin, Tuo Zhao
Machine Learning
LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection
Jahyeob Koo, Kio Yun, Byoungmo Koo et al. (+1 more)
Reconstruction errors in multivariate time-series anomaly detection may not reliably distinguish abnormal behavior from benign deviations.
Language-derived semantics offer complementary context, but existing
multimodal approaches may rely on time-associated paired textual information that is difficult to obtain consistently and is not provided by standard multivariate time-series anomaly detection
benchmarks. This setting poses two challenges: (1) conditioning masked reconstruction on window-specific semantics without exposing exact numerical targets or anomaly-specific cues, and (2) using a window-independent concept of normality as a complementary semantic reference rather than an independent anomaly detector. We propose LLM-Enhanced
Alignment and Reconstruction with Normality Guidance for Time Series (LEARN-TS), which uses a frozen
language model to construct two role-separated semantic representations without requiring temporally paired external text. Window-specific observation semantics encode temporal and cross-variable context without exact numerical values to guide channel-shared patch-masked reconstruction. A fixed,
dataset-agnostic normality
prompt provides a window-independent semantic reference for aligning normal representations and estimating normality discrepancy. At inference, masking each temporal patch once yields timestamp-level reconstruction evidence, conditionally modulated by discrepancy from a separate unmasked view. Across four
benchmarks, LEARN-TS achieves the highest mean performance in 13 of 16
dataset-metric comparisons. Controlled ablations examine observation conditioning, joint normality
alignment and scoring, and reference content, showing
dataset-dependent ranking benefits and modest average gains from semantic over random references.
Read the full abstract ▾
All authors Jahyeob Koo, Kio Yun, Byoungmo Koo, Jun-Geol Baek
Machine Learning
Same Loss, Different Gradients
Ningkang Peng, Xiaoqian Peng, Yifan He et al. (+4 more)
Differentiable learning typically assumes that the scalar objective evaluated in the forward pass and the gradient supplied to the optimizer in the backward pass describe the same mathematical object. We show that this correspondence can fail when probabilistic objectives rely on finite special-function recurrences, custom backward rules, and numerical clipping. In high-dimensional von Mises-Fisher learning, real numerical implementations can produce identical forward scores and losses at the same learning state while supplying different gradients and following different optimization trajectories. We characterize the structure of this mismatch in finite-start Bessel recurrence and show that classwise radial mismatch can compose through probabilities into a locally nonconservative update field. Evaluating the accuracy of special-function values and derivatives separately is therefore insufficient to characterize the realized learning objective. Motivated by this observation, we introduce AR/FR, a fixed-depth analytic realization that constructs a potential and its derivative jointly, ensuring forward-backward coherence by construction. We establish a uniform cubic-order error bound relative to the exact Bessel ratio over the entire nonnegative concentration axis and propagate this guarantee to learning scores and objectives. As representation dimension increases, the original finite recurrence becomes sequentially deeper, whereas the worst-case AR/FR error guarantee tightens cubically, jointly providing coherence, certified fidelity, and fixed-depth computation. These results suggest that a differentiable numerical primitive is defined by both the values it realizes and the derivatives it actually supplies to the optimizer; together, they constitute the numerical realization of the learning
algorithm.
Read the full abstract ▾
All authors Ningkang Peng, Xiaoqian Peng, Yifan He, Anjie Hu, Chao Tan, Peirong Ma, Yanhui Gu
Machine Learning
How Accurate Is Accurate Enough?
Ningkang Peng, Qianfeng Yu, Jingyang Mao et al. (+2 more)
How accurate must a numerical approximation be within a learning system? Primitive error alone cannot answer this question: errors of the same magnitude can have very different consequences for losses, predictions, and gradients at different learning states. We study this question through the learning objective itself. The objective weights classwise numerical errors nonuniformly according to the current state, so the importance of an error depends not only on its magnitude but also on the class it affects and the weight that class receives. For softmax cross-
entropy, we characterize this coupling between class weights and errors and derive the exact extrema of the signed loss change over pairings of fixed non-target probability and score-error multisets, with the target probability and target score error held fixed. Building on this structure, we establish finite-error guarantees that propagate primitive error to losses, probabilities, predictions, and feature gradients, then invert these guarantees to obtain a certified primitive tolerance for the current state under prescribed learning-level error requirements. We give a complete instantiation of the framework in high-dimensional von Mises-Fisher learning. Controlled interventions and a large collection of saved learning states show that identical primitive error can produce substantially different learning consequences, while certified numerical tolerances vary by orders of magnitude across states under the same learning-level requirements. These results show that the adequacy of a numerical approximation must be assessed in relation to the current learning state and the quantity to be preserved; numerical accuracy should itself be treated as part of the learning objective.
Read the full abstract ▾
All authors Ningkang Peng, Qianfeng Yu, Jingyang Mao, Xiaoqian Peng, Yanhui Gu
Machine Learning
Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?
Ningkang Peng, Qianfeng Yu, Jingyang Mao et al. (+4 more)
In probabilistic contrastive learning, a shared temperature is commonly interpreted as a shared similarity scale, but this interpretation does not hold for high-dimensional distributional class representations. We study the exact von Mises-Fisher (vMF) probabilistic score used by ProCo when representation dimension and class concentration grow jointly. We prove that the score retains a class-dependent leading angular gain $g_c=A_c/\tau$, where $A_c$ is the mean resultant length. This gain enters Softmax competition, pairwise decision boundaries, and feature gradients. On real CIFAR-LT, ImageNet-LT, and iNaturalist representations, the theory accurately predicts boundary movements and local gradient changes under the full vMF score. Classwise temperature adjustment also changes the cosine-zero intercept and finite-dimensional response. We construct intercept-preserving and Pure Angular controls to separate the leading gain from these accompanying changes. Complete gain equalization yields a shared-scale cosine prototype rule at leading order; a finite-dimensional margin condition guarantees agreement of the two classifiers. Across 16 frozen representation settings, prediction agreement is 98.43-99.99%, with disagreements concentrated at small cosine margins. In controlled contrastive-only training with the training-frequency prior, Pure Angular editing improves both learned representations at all tested CIFAR-10/100 imbalance factors and retains positive changes on ImageNet-LT. Thus vMF concentration not only describes class distributions, but also forms a decision and learning scale in high-dimensional probabilistic contrastive learning.
Read the full abstract ▾
All authors Ningkang Peng, Qianfeng Yu, Jingyang Mao, Xiaoqian Peng, Tingyu Lu, Peirong Ma, Yanhui Gu
Machine Learning
ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual Density
Xinhe Wu and Yadong Jin
Multimodal large
language models (MLLMs) offer a promising approach for recovering numerical data from scientific charts, but their ability to reconstruct chart data from visually dense figures remains poorly understood. Existing chart understanding
benchmarks primarily evaluate question answering or chart-level
reasoning and provide limited support for evaluating structured numerical reconstruction from scientific figures. We introduce ChartDensity-Bench, a
benchmark for evaluating MLLMs on structured numerical data reconstruction from compound chart figures under controlled visual density. Built from charts paired with source-level ground-truth data, ChartDensity-Bench systematically varies the number of simultaneously presented charts ($k\in{1,3,6,9}$), enabling controlled evaluation of density-induced degradation. We further propose a multi-dimensional evaluation framework covering structural reliability, reconstruction completeness, parseability, and numerical fidelity. Experiments on five recent MLLMs show that numerical reconstruction generally degrades as visual density increases, while the magnitude of degradation varies substantially across models. Chart-level paired comparisons further show that the same source chart can incur higher reconstruction error when embedded in denser visual contexts. These findings highlight visual density as an important and previously underexplored factor in MLLM chart data reconstruction and provide a systematic
benchmark for evaluating model robustness in this setting.
Read the full abstract ▾
Machine Learning
Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution
Shixuan Liu, Joan Serrà, Kin Wai Cheuk et al. (+6 more)
Training data attribution for
diffusion models aims to identify the training samples that influence a generated instance, but existing methods either require costly per-sample gradient computation or query-specific model optimization. Moreover, most methods attribute changes in a proxy loss rather than changes in the actual model's generative behavior. We address these limitations by formulating attribution directly with a local score discrepancy measure, which applies to any
diffusion variant (including DDPM, EDM, and flow matching), and by showing that such measure can be estimated without retraining, as a preconditioned gradient similarity. We instantiate this
estimator as Training-data Influence via score Discrepancy (TID), which uses Kronecker-factored
curvature to avoid random projections and per-sample gradient storage. We then distill TID into TIDE, a forward-only student trained online to reproduce the teacher's rankings from the
diffusion model's internal activations. Under counterfactual evaluation on CIFAR-10, ArtBench-10, and MS-COCO, TID matches or outperforms state-of-the-art approaches, while TIDE retains most of TID's accuracy at four to five orders of magnitude lower per-query cost, attributing generated samples in milliseconds and faster than the generation itself.
Read the full abstract ▾
All authors Shixuan Liu, Joan Serrà, Kin Wai Cheuk, Jinju Kim, Woosung Choi, Yukara Ikemiya, Wei-Hsiang Liao, Jiaqi W. Ma, Yuki Mitsufuji
Machine Learning
Learning Under Forgetting: Statistical Support-Selective Retention in Stochastic Training Dynamics
Fujie Gao, Zuyue Zhang and Gang Sun
Prior work has shown that neural networks exhibit implicit biases toward low-complexity structure (e.g., spectral bias), memorization dynamics, and compression-like effects during training, but a unified dynamical account of selective retention remains incomplete. We propose Repeated Reinforcement with Persistent Forgetting (RPF) dynamics, a minimal framework in which repeated exposure reinforces patterns and structures that recur in the data, while persistent forgetting attenuates learned information. This view treats forgetting not merely as a failure mode, but as a selection mechanism. We build the theory in three successive layers. First, in an independent-feature model, we derive an exposure-selective survival law and a support-dependent retention boundary characterizing which patterns persist under forgetting. Second, in a shared-parameter model, we show that forgetting induces spectral filtering over covariance modes, preserving strongly supported shared components while suppressing weak ones. Third, under small-step and norm/coding approximations, we show how RPF dynamics induce an implicit trade-off between data fitting and the cost of stored information, yielding Minimum Description Length (MDL)-like compression. Controlled experiments provide evidence for this reinforcement–forgetting selection mechanism in scalar
memories and a nonlinear shared network. Joint reinforcement and attenuation interventions shift conditional retention, while matched exposure counts reveal forgetting-dependent effects of reinforcement timing and changes in the composition of the retained set. Together, these results show that repeated reinforcement and persistent forgetting jointly provide a controllable source of inductive bias beyond neural architecture and scale.
Read the full abstract ▾
Machine Learning
dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale
Shixuan Liu, Tongli Zhou, Junwei Deng et al. (+2 more)
Training data attribution (TDA) estimates the contribution of individual training examples to model outputs. Most scalable TDA methods rely on per-example gradients, whose computation and use at LLM scale pose challenges in efficiency, compatibility, and extensibility. We introduce dattri-LLM, a TDA library that makes gradient-based attribution more practical at scale. For efficiency, dattri-LLM uses compact gradient representations and dynamically routes gradient operations based on a cost model. For compatibility, its capture mechanism collects per-example gradients from existing training loops that call backward(), without requiring changes to the loop or its configuration. This includes distributed training with DDP and FSDP and pipelines built with HuggingFace
Transformers, TRL, and OLMo. For extensibility, dattri-LLM exposes reusable gradient operations and training-time callbacks for implementing attribution methods and applications. These interfaces support a variety of attribution methods, including gradient similarity,
curvature-based influence, and trajectory-based methods, as well as applications that act on gradients during training, such as online data selection. On the same hardware and workload, dattri-LLM achieves 3.2x the throughput of the fastest competing library on average, scales multiple attribution methods to 110B-parameter models across four H200 GPUs, and offers superior attribution fidelity-cost trade-offs across a range of models with different model families and scales. The source code of dattri-LLM is available at https://github.com/TRAIS-Lab/dattri-llm.
Read the full abstract ▾
All authors Shixuan Liu, Tongli Zhou, Junwei Deng, Pingbang Hu, Jiaqi W. Ma