Machine Learning
Representation Signatures and Risk-Feedback Alignment in LLM Trading Agents
Weicheng Xue
We study behavioral
alignment and representation dynamics of large
language model (LLM)
agents in financial decision environments. TradeArena, an auditable trading-
agent testbed with risk reports, execution simulation,
memory, and replayable trajectories, lets us analyze how rationales, positions, and interventions evolve under
market stress. Code and data artifacts are available through the \href{https://github.com/weich97/TreLLM-public}{TradeArena repository}. We find pre-failure signatures: planning
embeddings drift from normal centroids, fused plan-risk representations separate normal from pre-drawdown states, and local
manifolds exhibit effective-rank contraction. Across 80 rolling failure anchors and eight LLM trajectories, this pattern persists across hash, LSA,
Transformer, and white-box hidden-state probes. Stress tests with CoT-free target weights, lexical controls, OHLCV noise, and false audits show that rationale-level contraction can vanish without rationales, while intent-space and fused signatures remain informative. Structured risk feedback can act as an external
alignment signal without fine-tuning, but not as a universal performance enhancer: true audit feedback improves calibration for some models, returns for others, and exposes cases where placebo or hidden feedback has higher short-horizon return but weaker
alignment diagnostics. A 51-stock intraday experiment reveals a correlation blind spot: LLM rationales justify exposure to coupled assets that the risk layer clips. Finally, a financial-audit task suite shifts comparison from “which model trades best” to whether models can audit trajectories, respect execution boundaries, reproduce artifacts, and avoid claim overreach. These results support a research claim, not a profitability claim: auditable risk feedback and representation trajectories reveal when LLM financial
reasoning is aligning, drifting, or failing.
Read the full abstract ▾
Machine Learning
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
Wei Huang, Andi Han, Mingyuan Bai et al. (+4 more)
Diffusion models generate high-dimensional data with remarkable quality, yet how training discovers and exploits low-dimensional
manifold structure remains incompletely understood. We analyze a two-stage collapse-and-refine procedure motivated by the small-noise score: its singular normal component identifies
manifold projection as the leading denoising target, while the remaining correction encodes density and geometry. Under suitable assumptions, we prove that annealed mean-field training asymptotically recovers the population denoiser and quantify the resulting
geometric alignment error. With the learned representation fixed, residual score learning reduces to convex random-feature regression. We establish generalization bounds that separate residual learning error, propagated projection error, and
geometric approximation bias, with statistical exponents governed by the intrinsic dimension. Under additional structural assumptions, we further derive an end-to-end sampling guarantee. Motivated by this analysis, we develop Score-induced Latent
Diffusion (SiLD), a practical two-stage framework combining low-noise denoising representation learning with latent
diffusion, without requiring KL regularization of the latent representation. Experiments on Stacked MNIST and molecular generation
benchmarks demonstrate competitive generation quality relative to architecture-matched VAE-based latent
diffusion baselines.
Read the full abstract ▾
All authors Wei Huang, Andi Han, Mingyuan Bai, Huanjian Zhou, Qixin Zhang, Taiji Suzuki, Kenji Fukumizu
Machine Learning
TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data
Cormac Cureton and Narges Armanfard
Prior-Data Fitted networks (PFNs) have been very successful in tabular contexts, handling prediction tasks in context. However, they are designed for single-task inference, meaning that predicting several target values within a context requires repeated forward calls and precludes inter-task information sharing. We propose TabPFN-MT, which is trained on an expanded multi-target synthetic prior to capture inter-task dependencies in context. This model uses an expanded $y$-encoder and a shared decoder head to enable multitask in-context learning and simultaneous inference. The model is uniquely specialized for small-to-medium
datasets by relying on in-context learning rather than traditional gradient-based training. Within this regime (averaging fewer than 1,000 samples), extensive evaluations across 344
datasets demonstrate that TabPFN-MT establishes a new state-of-the-art for deep tabular multitask learning. Furthermore, despite the inherent compute asymmetry of joint optimization, our model remains highly competitive with the latest state-of-the-art single-task ensembles. Notably, on multitask
datasets it achieves an overall Accuracy rank of 4.89, the highest average rank among all models tested. Crucially, TabPFN-MT delivers this highly competitive performance while reducing the inference cost for $T$ tasks from $O(T)$ to $O(1)$ forward passes, offering a massive computational efficiency improvement for multi-target tabular applications.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
Conflict-Free Replicated Data Types for Neural Network Model Merging: A Two-Layer Architecture Enabling CRDT-Compliant Model Merging Across 26 Strategies
Ryan Gillespie
All 26 neural network merge strategies we tested including weight averaging, SLERP, TIES, DARE, Fisher merging, and evolutionary approaches – fail the algebraic properties (commutativity, associativity, idempotency) required for conflict-free distributed operation. We prove that this failure is structural: normalisation-based merges cannot simultaneously satisfy all three properties. To resolve this, we present a two-layer architecture – CRDTMergeState – that wraps any merge strategy in a CRDT-compliant (Conflict-Free Replicated Data Type) layer. Layer 1 manages contributions via OR-Set CRDT semantics, where the merge operation is set union – trivially commutative, associative, and idempotent. Layer 2 applies merge strategies as deterministic pure functions over a canonically-ordered contribution set, with randomness seeded from the Merkle root. We prove that this separation guarantees Strong Eventual Consistency: all replicas receiving the same contributions compute identical merged models, regardless of message ordering. Empirical validation spans three tiers: controlled 4x4 tensors (104/104 tests pass), production-scale models up to 7.24B parameters (208 strategy-level tests, 43,368 layer-level property checks at capped tensor resolution), and multi-node convergence under gossip and partition healing (100 nodes, 20 orderings), with CRDT overhead below 0.5 ms. Because the wrapper is transparent, downstream performance is identical by construction, confirmed via byte-identical output verification. The reference implementation is available as crdt-merge v0.9.4.
Read the full abstract ▾
Machine Learning
Soft Learning
Mohammed Aledhari, Ali Aledhari, Fatimah Aledhari et al. (+1 more)
Modern machine learning forces practitioners to choose between powerful but expensive deep networks and fast but limited classical
algorithms. Here we introduce Soft Learning, a framework that maintains a library of heterogeneous specialists – spanning linear models, tree ensembles, kernel machines, and neural networks – and discovers provably optimal combination weights through cross-validated non-negative least squares. Soft Learning is guaranteed to match or exceed the best weighted combination of its specialists, trains over two orders of magnitude faster than deep networks on CPU alone (72-435x faster across tested configurations), provides inherent interpretability through learned weights that reveal which algorithmic paradigm best fits the data, and is future-proof: adding specialists is mathematically guaranteed to maintain or improve performance. Across 37
datasets (25 classification, 12 regression) against nine methods including CatBoost and tuned deep networks, Soft Learning ranks first on 70% of tasks, achieves the best mean rank (Friedman test, p = 1.12 x 10^-12), and is the only method to simultaneously excel at both classification and regression – all without GPU hardware or hyperparameter tuning. These results suggest a paradigm shift from "which
algorithm is best?" to "what is the provably optimal combination?" – a question Soft Learning answers with formal guarantees for any data modality.
Read the full abstract ▾
All authors Mohammed Aledhari, Ali Aledhari, Fatimah Aledhari, Mohamed Rahouti
Machine Learning
Zeheng Wang, Bo Zhao, Yijie Zhu et al. (+6 more)
Multimodal emotion recognition aims to integrate text, audio, and
video sources to understand human affective states. Although
multimodal large
language models excel at
multimodal reasoning, they typically treat
emotion categories as independent labels, ignoring the rich hierarchical taxonomy of human psychology. Moreover, lacking external contextual knowledge makes them highly susceptible to over-interpreting noisy cues, further complicating fine-grained
emotion classification. To address these issues, we propose HyperEmo-RAG, a
retrieval-augmented generation framework that leverages a structured emotional knowledge base. Our framework introduces two key innovations. 1) Hierarchical
hyperbolic grounding. Recognizing the inherent hierarchical tree structure of
emotion taxonomies, we jointly embed hierarchical
emotion labels and
multimodal samples into a continuous
hyperbolic space (Poincaré ball) and design a hierarchical beam-search deliberation process that progressively retrieves samples from coarse to fine-grained levels. 2) Structured evidence injection. Based on the retrieved evidence, we construct an evidence graph and inject the structured knowledge as explicit cognitive context into the LLM through a Tree-Aware
Attention mechanism and an EmotionGraphFormer, preserving the integrity of graph-structured information. Experiments on multiple
datasets demonstrate that HyperEmo-RAG significantly outperforms existing methods.
Read the full abstract ▾
All authors Zeheng Wang, Bo Zhao, Yijie Zhu, Zhishu Liu, Hui Ma, Ruixin Zhang, Shouhong Ding, Qianyu Xie, Zitong Yu
Machine Learning
Prediction Is Not Physics: Learning and Evaluating Conserved Quantities in Neural Simulators
Andrew Bukowski, Aditya Kothari, Simba Shi et al. (+1 more)
A
diffusion model trained on
Hamiltonian trajectories can achieve rollout MSE near $10^{-3}$, but the standard deviation of its energy over time is between 7500 and 36000 times larger than the ground-truth energy standard deviation, indicating a failure to preserve conservation laws. This gap motivates our central question of whether neural networks can learn or select globally conserved quantities from physical trajectories. We investigate this across three
Hamiltonian systems: projectile motion, pendulum, and spring-mass. We use a structured $T(v)+V(q)$ energy model, a black-box Conservation Discovery Network (CDN), a
polynomial CDN, and a conditional
diffusion baseline. The structured network reaches $R^2 \geq 0.9999$ against analytical energy on clean data, while the black-box CDN reaches $R^2 \geq 0.996$ when trained with temporal consistency plus a small
alignment loss to analytical energy at $t=0$ ($\lambda_{\mathrm{align}}=0.2$). With $\lambda_{\mathrm{align}}=0$, CDN Pearson $R^2$ collapses on pendulum and spring-mass ($< 10^{-3}$), showing that temporal consistency alone is not enough to reliably identify the true energy. Under $1\%$ additive Gaussian noise, the CDN outperforms the structured model on the projectile and spring-mass systems, suggesting that the CDN may be more robust to noisy inputs in this setting. However, the
polynomial CDN is sensitive to training configuration: it achieves $R^2=0.78$ under a short training schedule on the pendulum system, but reaches $R^2=0.9998$ with more training time and data, regardless of whether noise is added.
Read the full abstract ▾
All authors Andrew Bukowski, Aditya Kothari, Simba Shi, Ishir Rao
Machine Learning
To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents
Wei Shi, Ziheng Peng, Sihang Li et al. (+4 more)
LLM
agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call
benchmark, six models from three families show high call accuracy but much lower no-call accuracy, leaving overall accuracy in the 55%-70% range. We trace this to an Intrinsic Bias Hypothesis (IBH): the call/no-call decision mapping carries an activation-independent call offset, so the model favors call even at activation parity. Using Sparse Autoencoders (SAEs), we recover behavior-aligned feature bases for the call/no_call decision, reduce them to a signed activation margin, and estimate the offset directly. Across all six models, the model is decision-neutral only when no_call activation outweighs call activation, consistent with IBH. We then causally test IBH with Adaptive Margin-Calibrated Steering (AMCS), a closed-form counter-bias shift along SAE decoder directions. Cancelling the diagnosed offset mitigates over-calling and improves overall accuracy with a negligible drop in call accuracy. Our work recasts over-calling from an empirical phenomenon into a mechanistic object amenable to causal correction. Code is available at https://github.com/SKURA502/
agent-sae/.
Read the full abstract ▾
All authors Wei Shi, Ziheng Peng, Sihang Li, Xiting Wang, Xiang Wang, Mengnan Du, Na Zou
Machine Learning
Emergence of a Flow-Assisted Casting Strategy for Olfactory Navigation via Memory-Augmented Reinforcement Learning
Changxu Zhao, Dongxiao Zhao, Xin Bian et al. (+1 more)
In dynamic flow fields, various animals exhibit remarkable odor search capabilities despite relying on
stochastic detections. Interestingly, there exists an optimal time window for integrating these detections that maximizes search efficiency. To understand the underlying mechanism, we investigate the
navigation performance of Reinforcement Learning (RL)
agents in unsteady flows under varying
memory lengths and flow conditions. Without any predefined models, the
agents develop a flow-assisted casting strategy and adaptively adjust both the geometry of their search trajectories and the concentration threshold for initiating casting to maximize the success rate. The
agent's average speed toward the odor source exhibits a non-monotonic dependence on
memory length, which can be explained by the "sector-search" model.
Read the full abstract ▾
All authors Changxu Zhao, Dongxiao Zhao, Xin Bian, Gaojin Li
Machine Learning
A Multi-Dimensional Clustering Approach for Identifying Inborn Errors of Immunity
Nishad Kulkarni, Alexandra K. Martinson, Nicholas L. Rider et al. (+2 more)
Rare diseases such as inborn errors of immunity (IEI) require early diagnosis to prevent end organ damage and improve quality of life. Hurdles in accessing and curating large scale electronic health record (EHR) data limit routine data driven analyses to remain on the forefront of IEI and other rare disease trends. Development of machine learning (ML)
algorithms in IEI for pattern recognition as well as published methodology examining how to systematically process and integrate complex medical data is limited. Our proposed pipeline, including data curation and ML clustering
algorithms, is designed to recognize novel rare disease patterns and extract IEI- associated features from a national data registry. Our methodology for EHR data formatting and processing presents the pipeline that transforms raw immunologic lab data into vectors. This is further combined with hyperparameter tuning for diseases pattern recognition via clustering. This study refines IEI feature awareness, develops data tool kits for rare disease populations analysis, and expands on transforming complex medical records in data structures interpretable by unsupervised ML.
Read the full abstract ▾
All authors Nishad Kulkarni, Alexandra K. Martinson, Nicholas L. Rider, Michael Keller, Syed Muhammad Anwar
Machine Learning
ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models
Yujie Lin, Chengyi Yang, Zhishang Xiang et al. (+2 more)
Large
language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for
privacy and safety. Existing machine unlearning methods primarily rely on retraining or aggressive fine-tuning, which are either computationally expensive or prone to degrading related knowledge and overall model utility. In this work, we reformulate machine unlearning as a precise knowledge re-mapping problem via model editing. We propose ZeroUnlearn, a few-shot unlearning framework. It overwrites sensitive inputs by mapping them to a neutral target state and removing their original representations. ZeroUnlearn enforces representational orthogonality through a multiplicative parameter update with a closed-form solution, enabling efficient and targeted unlearning. We further extend ZeroUnlearn to a gradient-based variant for multi-sample unlearning. Experiments demonstrate that our approach outperforms existing baselines while preserving general model utility. Our code is available at the github: https://github.com/XMUDeepLIT/ZeroUnlearn.
Read the full abstract ▾
All authors Yujie Lin, Chengyi Yang, Zhishang Xiang, Yiping Song, Jinsong Su
Machine Learning · Cross-listed from eess.SP
Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis
Jana Armouti, Laura Hutchins, Jacob Duplantis et al. (+12 more)
Hospital readmission within 30 days of discharge is a leading driver of morbidity, mortality, and avoidable healthcare expenditure in congestive heart failure (CHF). Current clinical risk stratification tools rely primarily on non-imaging data and exhibit limited predictive performance. Point-of-care lung ultrasound (LUS) offers a sensitive, noninvasive window into the pulmonary congestion that characterizes CHF decompensation, yet its prognostic utility for readmission prediction remains largely unexplored. We present a pilot feasibility study, the first systematic machine learning study using B-mode LUS acquired during hospitalization to predict 30-day CHF readmission. Quantitative spatiotemporal
embeddings are extracted from a pretrained Temporal Shift Module (TSM) ResNet-18 encoder, and interpretable biomarker features are separately evaluated. Through structured ablations over lung view, temporal representation, multi-view fusion, and cross-lung augmentation, we identify the key imaging factors driving readmission risk. Our findings reveal that (1) dependent lower-lung regions (Left-3, Right-3) carry the strongest prognostic signal, consistent with their greater susceptibility to hydrostatic congestion; (2) temporal difference features between sequential examinations substantially outperform single-timepoint representations, highlighting the importance of capturing disease trajectory; and (3) multi-view feature concatenation yields the best overall performance, with our top MLP model achieving an F1 score of 0.80 (95% CI: 0.62-0.96). Biomarker analysis further reveals that pleural-line abnormalities, including breaks and indentations, are as informative as the canonical A-line and B-line markers. These results support POCUS-derived biomarkers as practical, interpretable tools for noninvasive CHF risk stratification.
Read the full abstract ▾
All authors Jana Armouti, Laura Hutchins, Jacob Duplantis, Thomas Deiss, Thales Nogueira Gomes, Keyur H. Patel, Seema Walvekar, Shane Guillory, Thomas H. Fox, Amita Krishnan, Ricardo Rodriguez, Bennett DeBoisblanc, Deva Ramanan, John Galeotti, Gautam Gare
Machine Learning
OPTNet: Ordering Point Transformer Network for Post-disaster 3D Semantic Segmentation
Nhut Le, Ehsan Karimi and Maryam Rahnemoonfar
Post-disaster damage assessment requires rapid and accurate semantic
segmentation of 3D point clouds to identify critical infrastructure such as damaged buildings and roads. Early Point
Transformers (e.g., PTv1, PTv2) relied on computationally expensive neighbor searching (k-NN) and Farthest Point Sampling (FPS). To improve efficiency, recent architectures like Point
Transformer V3 (PTv3) adopted static serialization methods, such as
Hilbert curves or Z-order, to organize unstructured points for window-based
attention. However, these fixed orderings are not optimal for capturing the complex geometry of disaster scenes. In this paper, we propose OPTNet (Ordering Point
Transformer Network), which introduces a learnable Point Sorter module. OPTNet utilizes a self-supervised ordering loss to dynamically predict an optimal permutation that maximizes the locality of the
attention mechanism. We evaluate our method on the 3DAeroRelief
dataset, significantly outperforming state-of-the-art baselines.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Sample-efficient inductive matrix completion with noise and inexact side-information
Yuepeng Yang and Cong Ma
Inductive
matrix completion (IMC) is a variant of low-rank
matrix completion that incorporates row and column side-information. In principle, it can reduce the effective dimension of the recovery problem from the ambient
matrix size to the dimension of the side-information features. Existing theory, however, does not fully realize this advantage in the noisy setting: sample-efficient guarantees only apply to noiseless recovery, while noisy guarantees require sample sizes comparable to ordinary
matrix completion. This paper closes this gap for noisy IMC. We analyze a nonconvex projected gradient descent
algorithm with spectral initialization and prove that, under exact side-information, it achieves linear convergence and stable recovery at a sample complexity governed by the effective side-information dimension rather than the ambient
matrix dimension. The key technical ingredient is a local regularity condition for the IMC loss that holds at this reduced sample size, despite the mismatch between the observation pattern and the side-information subspaces. We further extend the analysis to inexact side-information, showing that the same reduced sample complexity is preserved and that the estimation error degrades optimally with the level of subspace misspecification. Motivated by this trade-off, we also propose a penalized interpolation between IMC and ordinary
matrix completion that balances sample efficiency against robustness to imperfect side-information. Simulations and experiments on the MovieLens
dataset support the theoretical findings and illustrate the practical benefits of exploiting side-information in low-sample regimes.
Read the full abstract ▾
Machine Learning
The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
Faris Chaudhry
We develop a
geometric theory of projection heads in self-supervised learning by modeling the head as a trainable Riemannian metric on the backbone representation
manifold. We show that linear heads perform implicit subspace whitening, while nonlinear heads adapt local metrics to satisfy the specific topological constraints of the loss, with head depth empirically dictating this capacity. Analyzing dimensional collapse, we prove that smooth nonlinear heads natively induce negative
eigenvalues in the Hessian at collapsed
equilibria, making them unstable. We empirically validate this by continuously tracking the optimization geometry during training, which reveals that smooth activations like Swish can generate explicit negative
curvature to escape collapse, whereas linear and ReLU heads under continuous-time gradient flow cannot, relying instead on discrete-time optimization dynamics and BatchNorm. Finally, we geometrically characterize how metric degeneracy governs the information-invariance trade-off, explaining why the head must be discarded. Evaluated across contrastive and decorrelation-based objectives on foundation models, our results demonstrate that the projection head acts as a universal
geometric buffer, decoupling the semantic backbone from the rigid, destructive constraints of the pretraining objective.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
High-dimensional Limit of SGD for Diagonal Linear Networks
Begoña García Malaxechebarría, Courtney Paquette, Maryam Fazel et al. (+1 more)
Understanding the behavior of
stochastic gradient methods is a central problem in modern machine learning. Recent work has highlighted diagonal linear networks as a simplified yet expressive setting for analyzing the optimization and generalization properties of neural models. In this work, we show that in the high-dimensional regime,
stochastic gradient descent on diagonal linear networks is well-approximated by continuous dynamics governed by a
stochastic differential equation (SDE), which explicitly decouples the drift from the gradient noise. We further derive a deterministic partial differential equation whose solution propagates the relevant state of the iterates and characterizes the time
evolution of a broad class of observable statistics, including the risk,
curvature, and other metrics for optimality. Finally, we show that, under a suitable parametrization, the
stochastic dynamics are globally well posed and converge exponentially fast to zero risk with high probability, yielding a fully explicit non-asymptotic description of their long-time behavior. Numerical simulations corroborate our theoretical findings.
Read the full abstract ▾
All authors Begoña García Malaxechebarría, Courtney Paquette, Maryam Fazel, Dmitriy Drusvyatskiy
Machine Learning · Cross-listed from cs.CL
Why Do Safety Guardrails Degrade Across Languages?
Max Zhang, Ameen Patel, Sang T. Truong et al. (+1 more)
Large
language models exhibit safety degradation in non-English
languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety failure. We introduce a latent variable model, a Multi-Group Item Response Theory (IRT) framework, that decouples
language-agnostic safety robustness ($\theta$), intrinsic
prompt hardness ($\beta$), global
language processing difficulty ($\gamma$), and a
prompt-specific cross-lingual safety gap ($\tau$). Using the MultiJail
dataset, we evaluate the safety robustness of 61 model configurations across 5 closed-model families and 10
languages of varying resource, aggregating a
dataset of 1.9 million responses. Exploratory Factor Analysis shows safety is primarily unidimensional: models refuse different harm types mainly through a shared mechanism. Contrary to the expected trend that safety degrades largely in low-resource
languages, 22 model configurations are more vulnerable in English than in low-resource
languages. Low-resource
languages produce more uncertain responses (high
entropy) than high-resource
languages. Also, high-$\tau$
prompts cluster in physical harm categories like Theft and Weapons and lower-resource
languages, trends validated through cross-
dataset generalization. While global translation quality shows low correlation with $\tau$, severe mistranslations drive high-bias outliers, as validated by native speakers. Cultural and conceptual grounding mismatches may also contribute to $\tau$. In predictive validation, the IRT framework achieves $\mathrm{AUC} = 0.940$, and unlike rate baselines stays predictive when a whole
language is held out ($0.875$). Our framework reveals concept-
language vulnerabilities that aggregate metrics obscure, enabling fairer cross-lingual safety evaluation and targeted improvements in
dataset construction.
Read the full abstract ▾
All authors Max Zhang, Ameen Patel, Sang T. Truong, Sanmi Koyejo
Machine Learning
OpenJarvis: Personal AI, On Personal Devices
Jon Saad-Falcon, Avanika Narayan, Robby Manihani et al. (+10 more)
Personal AI stacks, like OpenClaw and Hermes
Agent, are becoming central to daily work, yet they route nearly every query (often over sensitive local data) to cloud-hosted frontier models. Replacing frontier models with local models inside existing stacks does not work: swapping Claude Opus 4.6 for Qwen3.5-9B drops accuracy by 25-39 pp across personal AI tasks like PinchBench and
GAIA. Existing stacks bundle agentic
prompts, tool descriptions,
memory configuration, and runtime settings around a specific cloud model. Only the
prompts can be tuned, and state-of-the-art
prompt optimizers close just 5 pp of the local-cloud gap on their own. This motivates a decomposed personal AI stack: one that exposes individual primitives which can be optimized individually or jointly to close the local-cloud gap. We present OpenJarvis, an architecture that represents a personal AI system as a typed spec over five primitives: Intelligence, Engine,
Agents, Tools &
Memory, and Learning. Each primitive is an independently editable field, making the stack end-to-end optimizable and measurable against accuracy, cost, and latency. Towards closing the local-cloud gap without surrendering local-model properties, OpenJarvis introduces LLM-guided spec search, a local-cloud collaboration in which frontier cloud models propose edits across the spec at search time, only non-regressing edits are accepted, and the resulting spec runs entirely on-device at inference time. With LLM-guided spec search, on-device specs match or exceed cloud accuracy on 4 of 8
benchmarks and land within 3.2 pp of the best cloud baseline on average. They also reduce marginal API cost by ~800x and end-to-end latency by 4x.
Read the full abstract ▾
All authors Jon Saad-Falcon, Avanika Narayan, Robby Manihani, Tanvir Bhathal, Herumb Shandilya, Hakki Orhun Akengin, Gabriel Bo, Andrew Park, Matthew Hart, Caia Costello, Chuan Li, Christopher Ré, Azalia Mirhoseini
Machine Learning
TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
Hanzhang Shen, Haoran Wu, Yiren Zhao et al. (+1 more)
Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context processing, the ability to handle
multimodal inputs, and structured multi-turn interactions with tool calling capabilities. As a result, their context exhibits structure that can carry different importance along three key axes: temporal recency to the current turn, modality such as text or image
tokens, and semantic role such as user queries, tool calls, observations, or
reasoning. These axes capture distinct
token behaviors and lead to different sensitivities to KV-cache compression. However, existing KV-cache quantization methods are typically homogeneous or exploit only heterogeneity on a single dimension, such as temporal proximity or modality, overlooking the interactions among them. To this end, we introduce TriAxialKV, a novel mixed-precision KV-cache quantization scheme that assigns each
token a triaxial tag, calibrates per-tag sensitivity, and allocates INT2/INT4 bitwidths under a fixed
memory budget. We implement TriAxialKV as an end-to-end serving system, comprising calibration, mixed-precision quantization and
memory management, and custom fused Triton decode kernels. When using Qwen3-VL-32B-Thinking as a computer-use
agent operating the OSWorld, TriAxialKV matches the accuracy of SGLang with BF16 KV cache while supporting 4.5$\times$ KV cache size and achieving 30% higher end-to-end throughput, when running on real GPU systems.
Read the full abstract ▾
All authors Hanzhang Shen, Haoran Wu, Yiren Zhao, Robert Mullins
Machine Learning · Cross-listed from cs.CV
Factorized Latent Dynamics for Video JEPA: An Empirical Study of Auxiliary Objectives
Santosh Premi
Joint-
Embedding Predictive Architectures (JEPA) are a promising framework for self-supervised
video representation learning, yet the behavior of auxiliary objectives in small-scale
Video-JEPA training is not well characterized. We report a small-scale empirical study of 18 auxiliary objective variants for
Video-JEPA across two pretraining regimes: single-
dataset (UCF-101) and mixed-
dataset (UCF-101 + Something-Something V2 + ImageNet-100). We evaluate frozen representations on three complementary
benchmarks: Diving-48 (fine-grained motion), SomethingSomething V2 (temporal
reasoning), and ImageNet-100 (appearance). Our experiments suggest that many auxiliary objectives exhibit capacity trade-offs: gains on one downstream capability often coincide with degradation on another. We then study FWM-HW-LD (Factorized World-Model with Hard-Region-Weighted Latent Dynamics), a training-time objective that separates the latent representation into appearance and dynamics subspaces and applies hard-region weighting to both JEPA prediction errors and latent dynamics errors. In our mixed-
dataset setting, FWM-HW-LD improves ImageNet-100 by +5.92 and SSv2 by +3.21 percentage points relative to the reference baseline, while remaining within 0.30 percentage points on Diving-48. These results indicate that latent factorization is a useful direction for studying auxiliary-objective trade-offs in
Video-JEPA.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference
Mengtian Yang, Zhekun Zhang, Mingheng Wu et al. (+3 more)
Deploying large-scale LLM training and inference with optimal performance is exceptionally challenging due to a complex design space of parallelism strategies, system optimizations, and hardware configurations. Accurate and rapid performance simulation is critical for guiding optimization efforts and system studies by validating "what-if" Hooker Figure hypotheses. To address this, we introduce Charon, a unified, modular, and fine-grained simulator for accurately predicting LLM performance. Experiments show Charon achieves high accuracy across different models and configurations, with an overall prediction error consistently under 5.35%, and even under 3.74% for training with a large-scale GPU cluster. In a practical inference deployment case, Charon discovered a configuration that improved system throughput over an engineering-tuned baseline, demonstrating its significant real-world value.
Read the full abstract ▾
All authors Mengtian Yang, Zhekun Zhang, Mingheng Wu, Jianwen Yan, Hanshi Sun, Li-wen Chang
Machine Learning · Cross-listed from cs.AI
From Imitation to Interaction: Mastering Game of Schnapsen with Shallow Reinforcement Learning
Ján Klačan and Sizhong Zhang
This paper investigates whether shallow neural network
agents can master the card game Schnapsen and challenge a strong search-based baseline, RdeepBot, which uses Monte Carlo sampling and lookahead search. Guided by a progressively more complex experimental design, we first evaluate a supervised learning
agent (MLPBot) trained on replay data and then a reinforcement learning
agent (RLBot) with the same shallow architecture trained through asynchronous Monte Carlo updates and experience replay. The results show that supervised imitation does not generalize well enough to defeat strong RdeepBot opponents, whereas reinforcement learning produces substantially stronger
agents. In the setting that focuses on the depth parameter of RdeepBot, the best performance is achieved when the learned value function is combined with deeper lookahead during gameplay, allowing RLBot to achieve statistically significant higher winning rates against the strongest evaluated RdeepBot baseline. In the sample-based setting, the gains are more conditional: the strongest performance appears at a relatively lower training num_samples parameter rather than increasing uniformly with stronger sampling.
Read the full abstract ▾
Machine Learning
When Bits Break Recourse: Counterfactual-Faithful Quantization
Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui et al. (+1 more)
Model quantization is widely used to reduce
memory, latency, and deployment cost, and is typically judged by whether predictive accuracy is preserved. In decision systems that provide algorithmic recourse, however, accuracy preservation is not sufficient: a small actionable change that flips the decision of a full-precision model may fail after quantization, or require a substantially larger intervention. This paper studies this deployment mismatch and introduces counterfactual sensitivity under quantization, a framework for measuring how compression changes recourse behavior. We propose two metrics: Validity Drop (VD), which measures the fraction of full-precision recourse actions that no longer achieve the target outcome after quantization, and Counterfactual Recourse Gap (CRG), which measures the increase in minimal recourse cost under the quantized model. To mitigate this failure mode, we introduce Counterfactual-Faithful Quantization (CFQ), a quantization-aware training method that jointly learns quantizer parameters and mixed-precision bit allocation while preserving the target prediction at teacher-generated recourse points. CFQ is compatible with standard LSQ/PACT-style quantizers and mixed-precision policies, and can also be instantiated as a training-free calibration procedure for post-training quantization. Experiments on Adult, German Credit, and COMPAS show that standard QAT and mixed-precision baselines can preserve accuracy while substantially degrading recourse stability. At matched accuracy and bit budget, CFQ consistently reduces VD and CRG; for example, on Adult, CFQ reduces VD/CRG from $0.121/0.162$ for an accuracy-centric mixed-precision baseline to $0.061/0.071$.
Read the full abstract ▾
All authors Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui, Ibrahim Ouahbi
Machine Learning · Cross-listed from quant-ph
Sparse Mamba Decoder for Quantum Error Correction: Efficient Defect-Centric Processing of Surface Code Syndromes
Samira Sayedsalehi, Nader Bagherzadeh, Maxim Shcherbakov et al. (+1 more)
Quantum error correction (QEC) is essential for building fault-tolerant
quantum computers, requiring decoders that are simultaneously accurate, fast, and scalable. Most state-of-the-art neural decoders achieve high accuracy but process the full dense syndrome array of size $O(d^2 R) $regardless of the actual error rate, where d is the code distance and R is the number of measurement rounds. At physically relevant error rates (p ~ 0.1%), fewer than 5% of syndrome entries contain active detection events – yet existing decoders process the entire syndrome volume. We introduce the Sparse Mamba Decoder (SMD), a defect-centric neural decoder that processes only the k active detection events using a 13-dimensional feature representation per defect and a Mamba state-space backbone, achieving $O(k)$ complexity. Across depolarizing, uniform
circuit-level, SI1000, and Google Sycamore experimental
benchmarks, SMD reduces the MWPM logical error rate by up to 49% at $d \le 5$ under SI1000 noise, runs 95-467x faster than the Tesseract near-MLD decoder and 232-463x faster than Belief Matching, and maintains nearly constant latency (24-57 us) across d = 3-9 under uniform
circuit-level noise. On the Sycamore experimental
dataset, the SMD ensemble matches or slightly surpasses the dense Mamba decoder of Varbanov et al. All results are obtained on commodity NVIDIA GPUs with 7.5-16M parameters, without specialized accelerators.
Read the full abstract ▾
All authors Samira Sayedsalehi, Nader Bagherzadeh, Maxim Shcherbakov, Jean-Luc Gaudiot
Machine Learning
Stress-Testing Neural Network Verifiers with Provably Robust Instances
David Troxell, Yulia Alexandr, Sofia Hunt et al. (+2 more)
Neural network verifiers aim to provide formal guarantees on model behavior, but existing verification
benchmarks are fundamentally limited by their lack of ground-truth labels. As a result, verifier evaluation relies on indirect heuristics, which prevents exact scoring and systematic study of verifier failure modes. We address this gap by introducing a reusable framework for generating verification instances whose ground-truth robustness labels are known a priori through analytic construction. Our framework led to the discovery of multiple numeric tolerance concerns and an implementation bug in popular verifiers, highlighting the need for ground-truth labels. Additionally, to systematically study verifier failure modes, we introduce the verification Difficulty Profile, a collection of estimable quantities capturing distinct sources of instance hardness. Using our framework and these profiles, we evaluate five state-of-the-art verifiers and show that different instances stress distinct aspects of the verification pipeline. We show that these results can aid the future development of verifiers as they provide actionable targets for improving numerical reliability, relaxation quality, and search behavior. Our code is publicly available: https://github.com/dtroxell19/VeriStressGT.git.
Read the full abstract ▾
All authors David Troxell, Yulia Alexandr, Sofia Hunt, Stephanie Lei, Guido Montúfar
Machine Learning
An Analytical Multiple Criteria Framework for Temporal and Dynamic Business-to-Business Customer Segmentation in Manufacturing
Muhammad Raees, Konstantinos Papangelis and Vassilis Javed Khan
In sales and marketing, customer
segmentation is an important tool for formulating strategies for customer treatment and supply chain management. Most
segmentation implementations rely on limited criteria, such as recency, frequency, and monetary (RFM) modeling, which often fail to capture complex business interactions. In this work, we design and evaluate a dynamic multi-criteria decision-making (MCDM) method in a business-to-business (B2B) manufacturing context by 1) extending RFM to dimensions of stability and growth, 2) integrating an adaptive and analytical hierarchical process to match business objectives, and 3) evaluating multivariate time-series clustering models. We then measure customer stability, tracking between-segment transitions, and
volatility over time, and apply a graph-based consensus model to further strengthen the analysis. We test the efficacy of the proposed method using a real-world manufacturing company
dataset to segment more than 3,000 B2B customers, showing strong robustness to temporal shifts. The implementation enables domain experts with preferential analytics to devise their strategies, providing effective decision support for B2B customer
segmentation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.NE
Evolutionary Extreme Learning Machine of ab-initio Energy Landscapes for Crystal Structure Prediction using Manta Ray Optimization with Levy Flight
Adrian Rubio-Solis
The Manta Ray Foraging Optimization
algorithm (MRFO) has proven to be a powerful heuristic strategy in the optimal solution of a large number of engineering problems. In this paper, an improvement of MRFO with Levy Flight is suggested for the training of extreme learning machines (ELMs) whose basic model is a Single Layer Feedforward Network (SLFN). The proposed methodology that we called Evolutionary EELM-MRFO-LF for short is implemented to the prediction of unrelaxed and relaxed formation energy compounds relative to ground state
crystal structure of pure components in binary systems. EELM-MRFO-LF follows the learning procedure of traditional Evolutionary ELMs in which first MRFO with LF is used to select the input weights and Moore-Penrose (MP) generalized inverse is applied to analytically determine the output weights. Levy Flight trajectory is implemented for increasing the diversity of the population of ELMs against premature convergence and the ability of avoiding getting trapped in a local optima. The performance of the suggested EELM-MRFO-LF is compared with other well-known nature-inspired
algorithms under similar conditions.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CE
Weighted Flow Matching and Physics-Informed Nonlinear Filtering for Parameter Estimation in Digital Twins
Yasar Yanik, Himadri Basu, Ricardo G. Sanfelice et al. (+1 more)
Digital twins (DTs) rely on continuous synchronization between physical systems and their virtual counterparts through online parameter estimation under uncertainty. In many practical settings, however, this task is challenged by low observability, weak excitation, nonlinear dynamics, and noisy or biased measurements. In this work, we develop a new mathematical framework that integrates Weighted Flow Matching (WFM) generative modeling with physics-informed nonlinear filtering to enhance parameter estimation in DTs. WFM relies on dynamic reweighting of training samples, which guides the generative model toward parameter regimes most informative of the evolving system state. This generative component is tightly coupled with a physics-informed filtering architecture based on the Unscented Kalman Filter (UKF), yielding a unified DT framework that combines data-driven probability transport with physically consistent state and parameter estimation. The effectiveness of the new integrated framework is demonstrated within a spacecraft DT architecture, where stable moment of inertia estimation is achieved under uncertain and noisy sensing, with significant performance improvements over established approaches such as Extended Kalman Filtering (EKF) and Ensemble Kalman Filtering (EnKF). These results highlight the potential of weighted generative modeling as a core mechanism for real-time DT synchronization in operational and mission-critical systems.
Read the full abstract ▾
All authors Yasar Yanik, Himadri Basu, Ricardo G. Sanfelice, Daniele Venturi
Machine Learning · Cross-listed from cs.RO
Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
Miranda Muqing Miao, Subin Kim, Brandon Yang et al. (+1 more)
Vision-
Language-Action (VLA) models leverage powerful perceptual priors from web-scale
Vision-
Language Model (VLM) pre-training, yet they remain surprisingly brittle in practice, frequently failing at simple robotic tasks. To mitigate this, we propose Contrastive Conceptor Activation Steering (COAST). COAST builds on the notion of a "conceptor", a linear operator that soft-projects data into the principal components of a target distribution. COAST uses conceptors to identify success-critical subspaces for a target robotic task from a few examples of success and failure rollouts. At inference time, it steers VLA latents into these identified success subspaces to improve task outcomes. Across three architecturally distinct neural policies (flow-matching VLA, autoregressive VLA, and
Diffusion Policy), COAST improves absolute mean simulation and real-
robot task success rate by over 20 and 40% respectively. The activation subspace geometry reveals that failure modes share substantial structure across tasks while success representations remain largely task-specific. When tasks share similar failure modes, this structure enables previously fitted conceptors to improve performance on new tasks without refitting. Ultimately, our results suggest that current VLAs retain substantial task-relevant knowledge in their latent representations, and that the action expert's decoding bottleneck could be mitigated by steering its residual stream toward task-relevant subspaces. COAST provides a lightweight, training-free path to unlocking these latent capabilities by steering the model towards its own "success" distributions.
Read the full abstract ▾
All authors Miranda Muqing Miao, Subin Kim, Brandon Yang, Lyle Ungar
Machine Learning · Cross-listed from cs.CV
A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation
Minhas Kamal, Hiranya Garbha Kumar and Balakrishnan Prabhakaran
Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and
geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions, introduces unique challenges for machine learning based methodologies. To combat these issues, diverse strategies have been developed, including converting to a format that has orderliness, extracting local geometry, and permutation-invariant or self-
attention-based processing. In this paper, our focus is directed towards deep learning models for three fundamental tasks in 3D
vision: point cloud classification, part
segmentation, and semantic
segmentation. We begin by formally defining point cloud data, followed by an in-depth discussion on its structural characteristics. Then, we categorize notable works based on their backbone structure and evaluate their performance on popular
benchmarks. Beyond empirical comparison, we offer insights into architectural innovations and limitations. We also outline open challenges and promising future directions for 3D point cloud understanding.
Read the full abstract ▾