artificialintelbulletin.com

Tag: cs.LG

  • Forecasting Without Full Identification: Reliability and Computational Cost in Clot-Growth Simulation

    Forecasting Without Full Identification: Reliability and Computational Cost in Clot-Growth Simulation

    [Submitted on 8 Aug 2026 (v1), last revised 13 Oct 2026 (this version, v2)]

    View PDF HTML (experimental)

    Abstract:We forecast clot growth from sparse early measurements with incomplete biochemical information. Using 1,000 simulated trajectories, we compare inverse search, which weights candidate inputs by their agreement with early observations, with a direct multilayer perceptron (MLP) predicting future clot size. Inverse search is more accurate when tissue factor alone, or tissue factor and fibrinogen, are unknown. When all five inputs are unknown, direct prediction achieves 2.16% pooled relative $L_2$ forecast error, outperforming search with 8,192 candidates using a forward MLP (3.25%) or latent neural ordinary differential equation model (3.36%). A conditional error bound separates candidate disagreement, weight on poor early fits, surrogate error, and candidate coverage. Increasing randomized quasi-Monte Carlo candidate budgets from 512 to 32,768 reduces numerical variation. A covariance score ranks additional assays by expected forecast value while accounting for measurement noise. At 10% range-scaled assay noise, incorporating assay uncertainty reduces forecast error from about 5% to below 3% for both surrogates. An independent reaction cascade verifies candidate integration against tensor quadrature, with mean normalized forecast-integration error below $10^{-5}$ at 32,768 candidates. These results demonstrate accurate clot-growth forecasting without full biochemical identification and support selecting prediction strategies and additional measurements according to accuracy, reliability, and computational cost.

    Submission history

    From: Lennon Shikhman [view email]
    [v1] Sat, 8 Aug 2026 14:47:28 UTC (964 KB)
    [v2] Tue, 13 Oct 2026 15:17:14 UTC (824 KB)

  • Tensor-reduced atomic density representations

    Tensor-reduced atomic density representations

    [Submitted on 2 Oct 2022 (v1), last revised 13 Oct 2026 (this version, v3)]

    View PDF HTML (experimental)

    Abstract:Density based representations of atomic environments that are invariant under Euclidean symmetries have become a widely used tool in the machine learning of interatomic potentials, broader data-driven atomistic modelling and the visualisation and analysis of materials this http URL standard mechanism used to incorporate chemical element information is to create separate densities for each element and form tensor products between them. This leads to a steep scaling in the size of the representation as the number of elements increases. Graph neural networks, which do not explicitly use density representations, escape this scaling by mapping the chemical element information into a fixed dimensional space in a learnable way. We recast this approach as tensor factorisation by exploiting the tensor structure of standard neighbour density based descriptors. In doing so, we form compact tensor-reduced representations whose size does not depend on the number of chemical elements, but remain systematically convergeable and are therefore applicable to a wide range of data analysis and regression tasks.

    Submission history

    From: James Darby [view email]
    [v1] Sun, 2 Oct 2022 01:08:50 UTC (197 KB)
    [v2] Tue, 6 Dec 2022 15:00:53 UTC (395 KB)
    [v3] Tue, 13 Oct 2026 12:58:16 UTC (224 KB)

  • PRIME: Frequency-Aware Unified Pruning and Merging for MoE Compression

    PRIME: Frequency-Aware Unified Pruning and Merging for MoE Compression

    [Submitted on 23 Sep 2026]

    View PDF HTML (experimental)

    Abstract:Mixture-of-Experts (MoE) models have emerged as an effective paradigm for scaling large language models, yet their massive parameter footprint poses severe memory challenges for deployment. Existing compression methods typically treat expert pruning and merging as disjoint operations and rely on greedy heuristics, often leading to irreversible information loss or representational pollution. In this paper, we propose PRIME, a unified optimization framework for MoE compression via adaptive PRunIng and MErging. PRIME casts the discrete prune-merge assignment step as a global Integer Linear Programming over a frequency-weighted surrogate objective, jointly selecting pruning and merging decisions while accounting for expert usage. We motivate the frequency-aware objective through an error-bound analysis under fixed representative assignments, and show that the formulation favors high-frequency experts as centroids, promoting routing stability. Extensive experiments on Qwen3-30B-A3B and Qwen3.5-122B-A10B demonstrate that PRIME achieves strong accuracy retention across knowledge, coding, math, and long-context tasks, while serving benchmarks of merged models quantify the memory and throughput benefits of expert compression in vLLM.

    Submission history

    From: Shanfeng Huang [view email]
    [v1] Wed, 23 Sep 2026 08:41:24 UTC (2,528 KB)

  • LADDER: A Long-Horizon Robot Manipulation Benchmark

    LADDER: A Long-Horizon Robot Manipulation Benchmark

    [Submitted on 13 Oct 2026]

    View PDF HTML (experimental)

    Abstract:General-purpose robot manipulation policies learn short-horizon skills effectively, but degrade rapidly on long-horizon tasks. Existing benchmarks cannot isolate failures because task horizon is either too short or entangled with scene and object variations. We propose LADDER, a long-horizon robot manipulation benchmark scaling from 1 to 10 subgoals within the same environment over three suites (SimplerEnv-Long, RobotArena-$infty$-Long, and RoboLab-Long), 145 tasks, eight categories, two embodiments, and 2,024 simulated episodes per system. We evaluate two orchestration paradigms: text subgoals for learned low-level policies (VoLo) and tool selection orchestration (CaP-X, GPT-Policy, PSP-Agent, TiPToP). Given the full instruction directly, low-level policies achieve 85.4% on single-subgoal tasks, but drop to near zero on extended tasks. While orchestration remedies this, it remains bounded by physical execution errors of the low-level policy rather than high-level planning and achieves only ~25%. Tool selection orchestration with GPT-Policy on GPT-6 Astra significantly outperforms learned-policy methods, but incurs significant time and cost budget and succeeds only ~62%. Real-world experiments across two embodiments confirm the collapse of the low-level policy and the gain from orchestration. Project website: this https URL

    Submission history

    From: Petko Petkov [view email]
    [v1] Tue, 13 Oct 2026 09:42:04 UTC (3,992 KB)

  • SIRNET: Causal Adaptation of Pretrained Embeddings for Semiparametric Treatment-Effect Estimation Under Surrogacy

    SIRNET: Causal Adaptation of Pretrained Embeddings for Semiparametric Treatment-Effect Estimation Under Surrogacy

    [Submitted on 29 Sep 2026]

    View PDF HTML (experimental)

    Abstract:Modern experiments increasingly produce rich post-treatment objects—such as text, images, and video—that may provide early surrogate signals for outcomes that are delayed, expensive, or observed only for a subset of participants. A pretrained encoder can turn such an object into a strong generic embedding, but the embedding is not trained for the estimation tasks required by a causal estimator and may emphasize information irrelevant to the causal target. We propose SIRNET, a Surrogate-Informed Representation adaptation framework for neural-NETwork-based causal estimation in the presence of unstructured post-treatment surrogates. Starting from pretrained surrogate embeddings, SIRNET learns a shared adapter jointly for outcome prediction, treatment propensity, and arm-specific surrogate marginalization, beyond the generic pretraining objective. The resulting covariate and surrogate representations provide a common interface for these nuisance tasks. The final treatment-effect estimate and confidence interval are obtained from cross-fitted orthogonal scores that attain the semiparametric efficiency bound under the stated nuisance-rate conditions. We also validate SIRNET’s performance in synthetic and semisynthetic experiments, as well as the Anti-Amyloid in Asymptomatic Alzheimer’s Disease (A4) trial, using frozen pretrained brain-MRI embeddings as surrogates for a long-term outcome.

    Submission history

    From: Lei Shi [view email]
    [v1] Tue, 29 Sep 2026 04:56:12 UTC (495 KB)

  • How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection

    How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection

    [Submitted on 2 Aug 2026 (v1), last revised 12 Oct 2026 (this version, v4)]

    View PDF HTML (experimental)

    Abstract:Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets that meet our audit, labeling, and calibration requirements. Focusing primarily on the audited DARPA TC E3 datasets, we apply a unified protocol with temporally separated test periods and validation-only checkpoint selection and threshold calibration, and ask which architectural claims are empirically supported. We find that alerting success and investigation utility can diverge sharply, as several systems surface attacks without providing enough process-level context to support forensic investigation. Across the four primary datasets, a simple allowlist built from executable names and paths observed during training matches or exceeds the selected learned baselines on key operating-point metrics, showing that comparable performance on these metrics is achievable using lexical novelty alone. Quantifying semantic signal quality through feature completeness and field entropy helps explain why several audited E3 datasets support alerting performance without reliably separating model architectures. Theia, however, provides the richest semantic signal and is the only primary dataset on which our reference model, Theseus, clearly improves both ranking and node-level recovery over the other learned systems. Overall, these findings reinforce the importance of interpreting architectural claims in PIDS together with the benchmark properties and evaluation protocol that produced them.

    Submission history

    From: Lorenzo Guerra [view email]
    [v1] Sun, 2 Aug 2026 19:27:49 UTC (1,529 KB)
    [v2] Sat, 15 Aug 2026 14:32:31 UTC (1,529 KB)
    [v3] Wed, 9 Sep 2026 15:09:04 UTC (1,587 KB)
    [v4] Mon, 12 Oct 2026 20:23:54 UTC (2,004 KB)

  • MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction

    MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction

    [Submitted on 10 Sep 2026]

    View PDF HTML (experimental)

    Abstract:Predicting cellular responses to chemical and genetic perturbations is a central test for AI virtual cells, yet many single-cell models reduce each condition to an average expression shift. This target is misaligned with perturbation biology: rare states, resistant subpopulations, and context-dependent effect sizes may coexist under the same intervention. MRFlow treats virtual-cell prediction as conditional transport between empirical single-cell measures. Control and perturbed cells are embedded in a variational latent state space, greedy low-cost supervision is constructed over detached minibatch states, and a conditional flow-matching vector field transports control populations toward perturbed populations. The field decomposes into a mechanism-structured affine dictionary, which recombines shared latent response operators with a low-rank condition-specific correction, and a spectrally controlled residual field for nonlinear cell-level variation. Genetic perturbations are encoded through a regulatory-graph GCN, chemical perturbations through Morgan fingerprints, and both enter the same conditional dynamics interface. Across eight gene and drug perturbation benchmarks, MRFlow attains the highest composite score while preserving competitive raw performance on differential-expression and distributional metrics. The results support latent distribution transport as a principled and empirically effective formulation for perturbation-aware virtual cell modeling.

    Submission history

    From: Hao’jie Yang [view email]
    [v1] Thu, 10 Sep 2026 09:55:56 UTC (2,613 KB)

  • Coding LLMs Can Be Harnessed to Learn Interpretable Models from Data

    Coding LLMs Can Be Harnessed to Learn Interpretable Models from Data

    [Submitted on 28 Sep 2026]

    View PDF HTML (experimental)

    Abstract:Since compact, interpretable classifiers correspond to simple programs, it is natural to ask if LLM-based coding agents can be used to learn interpretable models from data. In this paper we present a simple harness that repeatedly prompts a coding LLM to produce the next rule in a rule set, given a sample of labeled examples. We show that this approach is competitive with, and often superior to, state-of-the-art rule-learning methods on tabular data, especially with small training sets, and wins by large margins on text, including against another LLM-based rule learner; that this approach outperforms standard harnesses, and that the approach immediately leads to new kinds of interpretable models, since coding agents are not restricted to search a highly restricted hypothesis space. In addition to the advances made in learning interpretable models, these results are of interest because they introduce a new class of coding benchmarks – construction of interpretable classifiers – which includes quantitative measurements of output quality (i.e., test-set error) and existing mature “specialist coding algorithms” (i.e., existing learning methods).

    Submission history

    From: Aditya Kumar [view email]
    [v1] Mon, 28 Sep 2026 17:05:42 UTC (493 KB)

  • No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models

    No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models

    [Submitted on 4 Oct 2026 (v1), last revised 11 Oct 2026 (this version, v2)]

    View PDF HTML (experimental)

    Abstract:Text-to-image diffusion models can generate prohibited content, which motivates concept erasure through machine unlearning. Most erasure methods intervene at the text interface, through prompt modification or localized updates to text-conditioning weights, and they are evaluated by what the model outputs for given prompts. Such evaluation cannot see what the network still encodes. Latent-space auditing, which bypasses text conditioning and probes the denoising network directly, shows that erased concepts remain recoverable from internal representations. We find that this also holds for methods built to be robust against adversarial prompts, and that the problem grows with the number of erased concepts. We propose Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models (AVCE), a framework that grounds erasure in the model’s latent representations. AVCE audits the embedding neighborhood of each concept and condenses the discovered vulnerable directions into an anchor at the weakest geometric point. It edits cross-attention and self-attention projections in closed form at this anchor, then fine-tunes the two pathways with pathway-level auditing losses, using orthogonal gradient projection to consolidate multiple concepts. Experiments on SD v1.5, SDXL, and Flux 1.0 across object, explicit-content, and artistic-style unlearning show that AVCE reduces attack success rates by 5.07x and improves auditing scores by 3.84x over the strongest baseline, while preserving competitive generation quality.

    Submission history

    From: Kaiyuan Deng [view email]
    [v1] Sun, 4 Oct 2026 17:37:49 UTC (835 KB)
    [v2] Sun, 11 Oct 2026 20:57:56 UTC (833 KB)

  • GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games

    GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games

    [Submitted on 26 Sep 2026]

    View PDF HTML (experimental)

    Abstract:Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipelines, however, rely on a handful of hand-written games and on advantage estimators tied to them, so both the supply of games and the advantage estimate on a large corpus limit scaling. We present GameSmith, which scales both. An LLM synthesises games inside templates whose reward, observation, and hidden-information code is fixed. Each game is verified by seed-paired replay and by an independent re-implementation of its specification, then expanded into encoding, rule, and size variants, giving 26 new games in 29 families and 336 verified variants from the three SPIRAL templates. The model is distilled from the self-play of a larger teacher (Qwen3-32B) on these games and then trained by self-play reinforcement learning with CRAB, an advantage estimator that credits each decision against a shrinkage estimate of the expected return of its position and is defined on every variant. On Qwen3-4B-Base, distillation raises the 13-benchmark mean pass@1 from 45.5 to 62.5, above the three SPIRAL games at the same budget, and self-play with CRAB reaches 64.9. The ordering holds across models, and transfer grows with the number of game families.

    Submission history

    From: Waylon Li [view email]
    [v1] Sat, 26 Sep 2026 23:07:02 UTC (251 KB)