Machine Learning
Conf-Gen: Conformal Uncertainty Quantification for Generative Models
Gabriel Loaiza-Ganem, Kevin Zhang, Wei Cui et al. (+2 more)
Conformal prediction (CP) and its extension, conformal risk control (CRC), are established frameworks for quantifying uncertainty in supervised machine learning through formal guarantees. However, recent breakthroughs in artificial intelligence (AI) have been driven by unsupervised generative models, such as large
language models (LLMs) and image generators, which are not directly compatible with CP or CRC. In this work we introduce conformal generation (Conf-Gen), a general framework adapting CRC to generative tasks while relaxing its theoretical assumptions. Conf-Gen unifies and generalizes previous attempts to apply CP to LLMs, and extends conformal methodology to entirely new domains. We demonstrate the flexibility of Conf-Gen through some novel applications, including obtaining conformal guarantees on: image generators producing non-memorized images, conversational AI systems having asked enough clarifying questions, and the output of AI
agents being correct.
Read the full abstract ▾
All authors Gabriel Loaiza-Ganem, Kevin Zhang, Wei Cui, Marc T. Law, Kin Kwan Leung
Machine Learning
CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models
Venkat Akhil Lakkapragada
Large
language models have achieved strong
reasoning capabilities, though often at the cost of massive parameter counts and expensive inference. In this work, we explore a different direction: adaptive
reasoning depth in compact
language models. We present CosmicFish-HRM, a compact
language model built around a Hierarchical
Reasoning Module (HRM) that dynamically allocates computational effort during inference. Instead of applying fixed computation to every input, the model iterates through high-level and low-level
reasoning cycles and learns when to halt based on input complexity. CosmicFish-HRM combines this adaptive
reasoning core with modern
transformer components including Grouped Query
Attention, RoPE, and SwiGLU activations. While the additional
reasoning infrastructure introduces overhead at small scale, we hypothesize that this tradeoff becomes increasingly favorable as model size grows and the relative cost of the HRM core diminishes. Our results show that the model learns non-uniform
reasoning behavior, allocating different numbers of
reasoning steps across tasks and inputs. These findings suggest that adaptive
reasoning depth may offer a promising alternative to relying solely on parameter scale for
reasoning capability.
Read the full abstract ▾
Machine Learning
When LLM Reward Design Fails: Diagnostic-Driven Refinement for Sparse Structured RL
Youting Wang, Yuan Tang, Bowen Liu et al. (+2 more)
For sparse, structured reinforcement-learning tasks with semantic reward-function interfaces, LLM-generated reward shaping is better framed as debugging than one-shot generation. We study PPO-trained
agents using MiniGrid as core evaluation and MuJoCo reaching/locomotion as boundary stress tests. Our qualitative audit finds two recurring one-shot failure modes – reward flooding and semantic/API misunderstanding – and a rarer, less reliably distinguished weak-shaping case. We propose diagnostic-driven iterative refinement, using training diagnostics and a failure-mode taxonomy to guide reward-function revision. On sparse structured tasks with diagnosable reward failures, refinement improves DoorKey-8x8 from 2.3% success without shaping to 97.6%, and KeyCorridor from 31.2% one-shot to 86.7% with high seed-to-seed variance. Controls show these gains are not from generic retrying or extra training alone: metrics-only re-prompting causes large drops, while a static-vocabulary control recovers much of the gap. Thus taxonomy prompting is a major mechanism, with only partially isolated incremental evidence for dynamic labels. In
prompt-matched comparisons across Haiku 4.5, Opus 5, and DeepSeek V4 Pro, effects depend on task and model; none of the six contrasts survives family-wise correction. A four-call, episode-budget-matched population control is also competitive. Component-removal and sensitivity tests reveal calibration limits. In continuous control, success-based diagnostics can misfire in dense-reward locomotion; return-trend feedback removes one false-positive mechanism without robust locomotion gains. The method is bounded to sparse structured tasks with reliable structured interfaces under PPO training.
Read the full abstract ▾
All authors Youting Wang, Yuan Tang, Bowen Liu, Xuan Liu, Dingyan Shang
Machine Learning
Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems
Xin Li, Chenhan Xiao, Jonathan Cohen et al. (+3 more)
The rapid growth of AI-driven data centers and large-scale energy storage systems is increasing the reliance of power system operation on real-time measurement data and automated decision-making. However, many existing detection methods rely on statistical or data-driven analysis of measurements and can fail when attackers exploit the same data structure to craft stealthy perturbations. To illustrate this limitation, we demonstrate a blind False Data Injection Attack (FDIA) in which an Autoencoder learns the measurement
manifold and generates perturbations aligned with the Jacobian null space, thereby allowing the attack to evade both residual-based baddata detectors and time-series anomaly detectors. To mitigate data-driven FDIAs which exploit the null space, we propose a
topology-informed Cycle-Space Detector (CSD) that leverages the Cycle-Space of the network to impose structural constraints that enhance null space estimation. In addition, we prove that by using the Minimum Cycle Basis (MCB), the proposed CSD achieves the optimal generalization error for attack detection. By exploiting
topology-derived cycle constraints rather than relying solely on numerical null space estimation, the proposed method does not require precise line parameters and improves the separation between normal and attacked measurements. Simulation results on IEEE 14-, 30-, 57-, and 118-bus systems demonstrate that the proposed method effectively detects data-driven FDIAs under realistic measurement noise.
Read the full abstract ▾
All authors Xin Li, Chenhan Xiao, Jonathan Cohen, Aviad Elyashar, Yang Weng, Rami Puzis
Machine Learning
Sequential Physics-Constrained Neural Operator Forward Modeling for the $\textit{Norne}$ Reservoir System
Clement Etienam, Juntao Yang, Oleg Ovcharenko et al. (+4 more)
We develop a comprehensive mathematical and computational framework for sequential surrogate modeling of three-phase black-oil reservoir dynamics using neural operators, with particular emphasis on
Fourier Neural Operators (FNO) and their physics-informed variant (PINO). The application focus is the Norne
benchmark reservoir, defined on a heterogeneous $46\times112\times22$ grid ($N=113,344$
cells), with a production history spanning $T=30$ timesteps covering 3298 days. Our theoretical contributions are organized around four interlocking problems: (1) functional-analytic formulation in a product-Sobolev-space setting, including well-posedness of the implicit timestep map and sharp local Lipschitz estimates; (2)
covariate shift quantification, proving that the Wasserstein-2 distance grows as $W_2 \leq \varepsilon(L^n-1)/(L-1)$, with exponential population-risk discrepancy for $L>1$; (3) physics-constrained spectral stability, showing PINO training with $\lambda_R \geq \lambda^*_R$ reduces the learned Jacobian spectral radius to $\rho_F + C\lambda_R^{-1/2}$, yielding uniform-in-time rollout error $|\delta_n| \leq \varepsilon/(1-\rho)$; and (4) $K$-step TBPTT gradient analysis, deriving
geometric bias decay $O(\rho^K)$, optimal window $K^ = O(\log(T/\sigma^2))$, and Adam convergence $O(1/\sqrt{t}) + O(\rho^{K^*})$. Empirical validation confirms all theoretical predictions: autoregressive PINO surrogates sustain $R^2>0.99$ (oil), $R^2>0.90$ (gas), $R^2\approx 0.80$ (pressure), and monotonically improving $R^2$ (water) across the full 3298-day horizon, trained on eight NVIDIA B200 GPUs in under one hour. A 1000-member ensemble runs in under one minute on a single B200 GPU, giving a ${\sim}10^4\times$ wall-clock speedup over the OPM finite-volume simulator.
Read the full abstract ▾
All authors Clement Etienam, Juntao Yang, Oleg Ovcharenko, Nick Luiken, Tsubasa Onishi, Nefeli Moridis, Issam Said
Machine Learning
Spectral Guidance for Flexible and Efficient Control of Diffusion Models
Gabriel Moreira, Manuel Marques, João Paulo Costeira et al. (+1 more)
We introduce Spectral Guidance, a framework for controlling
diffusion models by leveraging the intrinsic geometry of the generative process. As data is progressively corrupted by noise, only a small number of features remain informative for control. We characterize them as the singular functions of a conditional expectation operator and show that they can be learned via a self-supervised objective. Once recovered, this basis enables the projection of arbitrary guidance signals, such as labels, CLIP
embeddings, or masks, directly onto the sampling trajectory. This approach allows for stable, high-fidelity control without retraining or denoiser backpropagation during sampling. Empirically, we improve conditional accuracy on CIFAR-10 by 37 percentage points over the strongest training-free baseline while offering $4\times$ faster sampling. Moreover, the same representations that support label and CLIP guidance also enable spatial control, such as mask-based guidance, without auxiliary models. Finally, our framework reveals a phase transition in the generative process, pinpointing the optimal time window for effective guidance.
Read the full abstract ▾
All authors Gabriel Moreira, Manuel Marques, João Paulo Costeira, Chenyan Xiong
Machine Learning
Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models
Prasanth K K
Low-Rank Adaptation (LoRA) has emerged as a widely adopted approach for adapting large
language models, yet the internal representational changes induced by LoRA fine-tuning remain insufficiently understood. In this work, we investigate the geometry of LoRA-induced representations using Sparse Autoencoders (SAEs). We introduce a delta activation framework that isolates the adapter-specific contribution to the residual stream. Using Gemma-2-9B with LoRA ranks 4, 8, 16, and 32, we train adapter-specific SAEs across multiple
transformer layers and compare their learned feature spaces with pretrained SAE dictionaries. We evaluate representational
alignment using cosine similarity between decoder directions, principal-angle analysis of feature subspaces, and Centered Kernel
Alignment (CKA) between activation representations. Across layers and ranks, we consistently observe comparatively weak
geometric alignment between LoRA-induced feature dictionaries and pretrained SAE features. Adapter-specific SAEs also reconstruct delta activations more effectively than pretrained SAEs, suggesting that LoRA updates occupy partially distinct representational structure within the residual stream. Additionally, feature density increases with rank and depth, while
geometric divergence remains relatively stable across ranks. These findings provide empirical evidence that LoRA fine-tuning can induce feature structures that are not fully captured by pretrained interpretability dictionaries, with implications for mechanistic interpretability, adaptation analysis, and safety
auditing of fine-tuned
language models.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought
Jiacheng Lu, Yiming Li, Tao Song et al. (+4 more)
Large
Language Models with Chain-of-Thought
reasoning capabilities represent valuable intellectual property, yet existing black-box watermarking methods often trade robustness for
reasoning fidelity by perturbing final answers or relying on fragile trigger patterns. We propose BiCoT, a watermarking framework that embeds ownership signals into the internal geometry of
reasoning traces by aligning high-saliency structural anchors with a private signature subspace while regularizing ordinary control
tokens to preserve semantic capacity. This design couples the watermark with
reasoning-relevant representations, making removal difficult without disrupting the features that support coherent
reasoning. To enable verification under model theft and representation drift, we introduce Robust Subspace Registration (RSR), a Top- logprob-based black-box verifier that uses sentinel
tokens to calibrate systematic shifts in the output distribution. Experiments show that BiCoT preserves
reasoning fidelity across diverse complex
reasoning tasks while achieving robust detection under fine-tuning, quantization, model-level perturbations, and adaptive output-level attacks across in-domain and out-of-distribution settings.
Read the full abstract ▾
All authors Jiacheng Lu, Yiming Li, Tao Song, Weijian Wang, Wenjie Qu, Haibing Guan, Jiaheng Zhang
Machine Learning
Ziyang Zheng, Zeju Li, Xiangyu Wen et al. (+5 more)
Context
distillation compresses contextual information into model parameters, yet existing methods often ignore how multiple distilled latent
memories should be stored, retrieved, and safely activated in non-oracle settings. We formulate context
distillation as a latent
memory management problem. We distill each context into an independent LoRA adapter, forming a modular
memory bank that enables explicit
memory selection. Given a query, our framework retrieves candidate
memories, routes the query to the most suitable adapter, and uses a Self-Gating mechanism to decide whether latent
memory should be activated. To improve efficiency, we further introduce cache sharing to reduce management overhead during inference. Experiments show that our method substantially outperforms baselines with
retrieval, while Self-Gating improves robustness by deactivate unnecessary latent
memories.
Read the full abstract ▾
All authors Ziyang Zheng, Zeju Li, Xiangyu Wen, Jianyuan Zhong, Junhua Huang, Lei Chen, Mingxuan Yuan, Qiang Xu
Machine Learning · Cross-listed from cs.IR
Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap
Sicong Wang, Ruiting Dong, Yue Liu et al. (+7 more)
Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide integrated service recommendations, we focus on the task of Generative Spatiotemporal Intent Sequence Recommendation (GSISR), which aims to generate intent sequences that are logically coherent and physically executable within complex spatiotemporal contexts. While LLMs offer strong
reasoning potential for GSISR, direct industrial deployment is limited by high inference latency and context-mismatched or physically infeasible plans. To address these challenges, we propose a generative framework, GPlan, that internalizes LLM
reasoning into lightweight models through two components. First, to enable
reasoning under strict latency constraints, we introduce Progressive Implicit CoT
Distillation, which compresses explicit
reasoning processes into reserved latent
tokens, allowing small models to inherit complex planning logic without generating long
reasoning text. Second, to address the disconnect between general knowledge and real-world constraints, we design Spatiotemporal Counterfactual DPO. By aligning the model with counterfactual context-plan pairs, we improve sensitivity to spatiotemporal context and reduce context-mismatched plans. Offline experiments and online A/B testing demonstrate that our approach improves sequence coherence and context responsiveness. Our implementation and the anonymized GSISR
dataset are available at https://github.com/alibaba/GPlan.
Read the full abstract ▾
All authors Sicong Wang, Ruiting Dong, Yue Liu, Bowen Zheng, Jun Meng, Jie Li, Shuaijun Guo, Yu Gu, Fanyi Di, Xin Li
Machine Learning · Cross-listed from q-bio.QM
Computational Modeling of Antibody-Antigen Complexes: PLM-Based and MSA-Based Approaches
Xiao Luo
Antibodies play a central role in the immune response by specifically recognizing and neutralizing antigens, and therapeutic antibodies have become major drugs for cancer and autoimmune diseases. However, their discovery still relies on extensive in vitro screening, and accurate computational modeling of antibody structures and antibody-antigen interactions can prioritize candidates, reduce experimental burden, and accelerate rational design. Despite recent advances in high-accuracy
protein and complex prediction, a persistent performance gap remains for antibody-related tasks compared with general
protein-
protein interactions, limiting downstream design. This thesis investigates why antibody-related tasks are harder and proposes improvements along two complementary directions. First, we investigate
protein language model (PLM)-based methods for antibody and antibody-antigen structure prediction. Using
embeddings from multiple PLMs, our approach achieves the best CDR-H3 accuracy among compared PLM-based methods on antibody monomer prediction. Extending it to complex prediction does not generalize: without co-evolutionary signals between antibody and antigen, single-sequence PLM representations do not reliably identify binding interfaces. Second, we develop two MSA-based interventions for antibody-antigen complex prediction: MSA refinement, which combines CDR-focused filtering with depth recovery from a larger sequence database, and convergence-aware recycling, which selects a stable intermediate recycle state for final
diffusion sampling. Together, these interventions provide consistent gains over the AlphaFold3 baseline on a held-out antibody-antigen test set. Because the methods modify MSA construction and recycling behavior rather than model parameters, they apply without retraining or weight access.
Read the full abstract ▾
Machine Learning
PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective
Yangyi Huang, Ruotian Peng, Zeju Qiu et al. (+4 more)
Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large
language models, yet evaluations largely emphasize downstream accuracy while overlooking the retention of pretrained capabilities. We argue that PEFT should be assessed through the stability-plasticity dilemma: the trade-off between target-task adaptation and resistance to forgetting. We introduce PEFT-Arena, a
benchmark that jointly measures downstream performance and general capability retention. Across methods, we find distinct stability-plasticity profiles; under comparable parameter budgets, orthogonal finetuning achieves the most favorable Pareto frontier. To explain these differences, we analyze PEFT updates from two
geometric perspectives. In weight space, spectral analysis reveals how parameterizations interact with the pretrained singular-value structure. In activation space, retention metrics show whether finetuning preserves or distorts general-capability representations, with forgetting linked to non-isometric representation distortion. Finally, an analysis shows that final SFT checkpoints often overshoot a better target-retention operating point. Inspired by this, we present case studies of a post-hoc improvement with path-wise rewinding.
Read the full abstract ▾
All authors Yangyi Huang, Ruotian Peng, Zeju Qiu, Jiale Kang, Yandong Wen, Bernhard Schölkopf, Weiyang Liu
Machine Learning · Cross-listed from cs.RO
Beyond Binary: Sim-to-Real Dexterous Manipulation with Physics-Grounded Contact Representation
Jiahe Pan, Stelian Coros, Jitendra Malik et al. (+1 more)
A primary bottleneck in contact-rich manipulation is the difficulty of collecting real-world data. Sim-to-real reinforcement learning offers a scalable alternative, but the simulation-reality gap prevents information-dense modalities like touch from being effectively used. Existing sim-to-real methods often mitigate this gap by simplifying tactile data into coarse low-dimensional features – sacrificing the richness required for complex manipulation. In this work, we introduce Center-of-Pressure (CoP), an effective tactile representation grounded in physical principles that preserves dense contact information while maintaining robustness for sim-to-real transfer. To support this representation, we propose a sensor calibration scheme based on differentiable dynamics, enabling the estimation of taxel orientations without requiring ground-truth force measurements. We evaluate CoP on two blind, challenging contact-rich manipulation tasks: peg-in-hole insertion and ball balancing. Across both tasks, policies conditioned on CoP achieve zero-shot sim-to-real transfer on a multi-fingered hand, and outperform both coarse binary-contact and raw-taxel baselines. Analysis of learned policy states further suggests that CoP-conditioned policies encode task-relevant physical properties, such as object mass, as an emergent byproduct of control.
Read the full abstract ▾
All authors Jiahe Pan, Stelian Coros, Jitendra Malik, Toru Lin
Machine Learning
Affective Music Recommendation: A Rollout-Based World Model for Offline Preference Optimization
Audrey Chan, Aaron Labbé, Jacob Lavoie et al. (+4 more)
Functional music applications, from consumer focus and sleep aids to clinical interventions, share a distinctive recommendation problem: success is defined by the listener's affective state, but online experimentation on
emotion is ethically constrained, particularly for clinical populations who cannot reliably skip a song or report distress. We describe AMRS, the Affective Music Recommendation System deployed on LUCID's health-and-wellness platforms, which serve clinical users (primarily older adults with neurocognitive conditions) and consumer-wellness users across energize, focus, calm, and sleep modes. AMRS is built around a rollout-based world model: a causal
transformer trained on logged listening data to jointly predict engagement, binary rating, and self-reported valence and arousal. The world model serves both as an in-silico simulator for offline policy training and as a stress-testing tool before deployment. A recommender policy initialized by behaviour cloning is fine-tuned offline with Direct Preference Optimization (DPO) against a configurable multi-objective utility function. Under a strict cold-start protocol, the world model predicts both behavioural and affective signals with usable fidelity; DPO improves predicted valence and arousal over the cloned baseline while maintaining a similar diversity profile and avoiding the distributional collapse produced by greedy optimization. We position the work as an early deployed validation of a methodology for affective recommendation when online experimentation is ethically untenable.
Read the full abstract ▾
All authors Audrey Chan, Aaron Labbé, Jacob Lavoie, Jordan Bannister, Arsène Fansi Tchango, Guillaume Lajoie, Laurent Charlin
Machine Learning · Cross-listed from cs.CV
AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
Zhen-Hao Xie, Yu-Cheng Shi and Da-Wei Zhou
Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual
embeddings obtained from template
prompts, e.g., “a photo of a [CLASS]”. This seemingly monolithic matching process can be decomposed into two conceptually distinct stages: attribute extraction and attribute aggregation. For example, a model may recognize cat using attributes such as fur texture and whiskers. When learning a new class like car, the model must extract additional attributes like wheels and adjust how they are aggregated in the shared representation space. However, since only data from the current task is available, incremental updates can bias both attribute extraction and aggregation toward new classes, leading to catastrophic forgetting. Therefore, we propose AREA for attribute extraction and aggregation in CLIP-based CIL. To stabilize extraction, we anchor class-level visual and textual attributes on the hyperspherical
embedding space via principal geodesic analysis. To stabilize aggregation, we learn lightweight task-specific experts with scoring and residual refinement, regularized by a variational information bottleneck objective. During inference, we perform routing over task attribute
manifolds via optimal transport for more concise prediction. Experiments show that AREA consistently outperforms SOTA methods. Code is available at https://github.com/LAMDA-CL/ICML2026-AREA.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration
Xinchen Zhang, Bowei Liu, Jiale Liu et al. (+7 more)
Visual outcomes are increasingly central to
multimodal large
language models, making reliable and fine-grained verification essential for scaling generalist foundation models. In this work, we investigate
multimodal meta-verification, which leverages verifier-generated rationales rather than decision-only signals, and explore how to effectively incorporate meta-verification feedback into
multimodal verifier training. We identify two key findings. First, symbolic verifier outputs (e.g., bounding boxes) outperform textual explanations as meta-verification rationales, enabling efficient rule-based reinforcement learning rewards while avoiding reliance on model-based rewards from auxiliary judge models. Second, decoupling reinforcement learning objectives for binary judgment and meta-verification substantially outperforms joint reward optimization, due to intrinsic differences in output structure and learning dynamics. Based on these insights, we train OmniVerifier-M1, a generalist visual verifier leveraging symbolic meta-verification and decoupled reinforcement learning. OmniVerifier-M1 provides robust verification and fine-grained error localization, and further enables M1-TTS, a verifier-driven agentic generation system achieving dynamic region-level self-correction. This approach paves the way for more reliable, interpretable, and fine-grained
multimodal verification, supporting safer and more controllable foundation model deployment.
Read the full abstract ▾
All authors Xinchen Zhang, Bowei Liu, Jiale Liu, Chufan Shi, Yizhen Zhang, Junhong Liu, Youliang Zhang, Zhiheng Li, Yujiu Yang, Ling Yang
Machine Learning · Cross-listed from cs.CV
HoloQ-VLA: Uniform W4A4 Quantization of Vision-Language-Action Models
Xinyu Wang, Mingze Li, Sicheng Lyu et al. (+6 more)
Vision-
Language-Action (VLA) models unify perception,
reasoning, and control in a single policy, but their multi-billion-parameter backbones and
diffusion-based action heads make on-device deployment prohibitively expensive. Low-bit post-training quantization (PTQ) is the natural remedy, yet the
diffusion action head that emits continuous control signals is highly sensitive to it: a few weight and activation outliers are enough to destabilize the head, so prior work leaves it at full precision or falls back to mixed-precision schemes, and uniformly quantizing the whole model to low bit-width remains an open challenge. We present HoloQ-VLA, the first training-free PTQ framework that compresses both the
language backbone and the entire
diffusion action head to uniform W4A4 precision without mixed-precision allocation. Instead of trading weight quality against activation quality, HoloQ-VLA targets the two outlier sources with complementary transforms: a weight-adapted rotation composed with an activation-dispersing Hadamard transform, together with per-step scaling that absorbs the dynamic-range drift exhibited by the action head across denoising steps. On LIBERO, HoloQ-VLA compresses Pi-0.5 and GR00T-N1.5 to W4A4 with 98.0% and 87.8% task success rates, matching or exceeding their FP16 references of 97.1% and 87.0%, while reducing the static
memory footprint by 74.2%. Real-world manipulation experiments further demonstrate that HoloQ-VLA maintains smooth and accurate control across diverse real-world scenarios.
Read the full abstract ▾
All authors Xinyu Wang, Mingze Li, Sicheng Lyu, Dongxiu Liu, Kaicheng Yang, Ziyu Zhao, Yufei Cui, Xiao-Wen Chang, Peng Lu
Machine Learning · Cross-listed from cs.AI
CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models
Abhilash Durgam, Nyle Siddiqui, Jeffrey A. Chan-Santiago et al. (+3 more)
Electroencephalography (
EEG) is a critical, non-invasive method to monitor electrical
brain activity. EEGs can span anywhere from a couple seconds to multiple hours, posing a major hurdle for existing deep learning methods due to two major factors: (1) existing
EEG models are predominantly built upon the
attention mechanism, incurring quadratic scaling as the sequence length increases, and (2) raw
EEG signals must be processed in a sliding-window fashion due to fixed-length input requirements, preventing global understanding of the entire signal. To this extent, we propose CaMBRAIN - the first Causal, Mamba-based state space model (SSM) capable of real-time inference of
EEG signals, arguing that bidirectional approaches are needlessly expensive given the causal, unidirectional nature of
EEG. However, training such a model is non-trivial, as crucial
EEG events can be extremely brief - within fractions of a second - yet separated by long intervals spanning minutes. Current
EEG methods use self-supervised objectives that optimize for signal reconstruction, but these are not well suited for streaming SSMs; they fail to explicitly train the hidden state to retain the salient long-range context needed for streaming inference. We therefore introduce a multi-stage self-supervised training pipeline specifically tailored to encourage long-range
memory retention and strong performance on
EEG signals, while preserving the linear-time complexity of state space models. CaMBRAIN achieves state-of-the-art (SOTA) results across 3 different
EEG datasets with >10x higher throughput than existing models, enabling the first model capable of long-range, continuous inference of variable-length
EEG signals.
Read the full abstract ▾
All authors Abhilash Durgam, Nyle Siddiqui, Jeffrey A. Chan-Santiago, Qiushi Fu, Elakkat D. Gireesh, Mubarak Shah
Machine Learning · Cross-listed from cs.CV
Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions
Thomas Vitry, Kieran Edgeworth, Stefan Wermter et al. (+1 more)
Vision classifiers can exploit spurious correlations, achieving high in-distribution accuracy yet failing under distribution shift. Existing approaches to bias mitigation and analysis often depend on curated
datasets, spurious-attribute or group labels, or retraining, which may be infeasible once a model is deployed or the relevant bias is unknown. We present a bias-label-free, post-hoc method for identifying spurious concepts in frozen
vision models, relying only on standard class labels from a held-out audit
dataset. For each target class, we collect patches from inputs predicted as that class and apply non-negative
matrix factorization to intermediate activations to obtain a bank of interpretable concept vectors. Candidate concepts are then ranked with a bias
estimator derived from their interaction with backpropagated gradients on misclassified examples: bias concepts tend to get activated when correcting false negatives and suppressed when correcting false positives. On Colored MNIST and Waterbirds the method recovers concepts aligned with the known spurious cue, and on CelebA it surfaces decision-relevant directions that only partially coincide with the annotated gender attribute; suppressing the top-ranked concepts at inference time improves worst-group accuracy by up to 17.9 percentage points on Waterbirds and 10.4 on CelebA without any retraining or parameter updates. Our method identifies decision-relevant spurious directions that need not coincide with annotated ones, providing both an interpretable
auditing tool and an actionable debiasing handle for frozen
vision models. Code is available at https://github.com/vitryt/label-free-bias-identification.
Read the full abstract ▾
All authors Thomas Vitry, Kieran Edgeworth, Stefan Wermter, Jae Hee Lee
Machine Learning
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
Suji Kim, Kangsan Kim and Sung Ju Hwang
Computer-use
agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use
agents are more practical specialization targets, but they remain substantially weaker and exhibit uneven domain-specific failures. A straightforward remedy is to synthesize large-scale training data for the target domain, yet we find that this naive approach yields only marginal improvements. Building on this observation, we introduce LearnWeak, an annotation-free specialization framework for small computer-use
agents that uses a stronger reference
agent to identify the student's weaknesses in the target domain, synthesize targeted tasks, and construct supervision automatically. LearnWeak further introduces an error-aware specialization objective that disentangles planning and execution errors, enabling more behaviorally precise updates than broad uniform supervision. On OSWorld, LearnWeak achieves average gains of 11.6 and 11.1 percentage points over EvoCUA-8B and OpenCUA-7B, respectively, across eight domains. We also validate that our student-aware
dataset generation and training approaches outperform existing autonomous trajectory generation and training baselines. Our work highlights the importance of student awareness in both data synthesis and
agent training, pointing toward a more principled and efficient path for specializing small computer-use
agents in diverse domains.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Rethinking Memory as Continuously Evolving Connectivity
Jizhan Fang, Buqiang Xu, Zhixian Wang et al. (+12 more)
Existing
memory-augmented LLM
agents often treat
memory as a static repository with pre-defined representations and fixed
retrieval pipelines, which is brittle in dynamic agentic environments where feedback, task variation, and heterogeneous signals continuously reshape what should be remembered and how it should be connected. To address this, we propose FluxMem, a connectivity-evolving
memory framework that models
memory as a heterogeneous graph and progressively refines its
topology through three stages: initial connection formation, feedback-driven refinement, and long-term consolidation. During execution, FluxMem repairs missing links, prunes interference, aligns abstraction granularity, and distills recurrent successful trajectories into reusable procedural
circuits, guided by one metric for
memory generalizability and evolutionary maturity. Across three fundamentally distinct
benchmarks including LoCoMo, Mind2Web, and
GAIA, FluxMem achieves consistent state-of-the-art performance, demonstrating strong adaptation and generalization in complex agentic environments. The code will be open-sourced in https://github.com/zjunlp/LightMem.
Read the full abstract ▾
All authors Jizhan Fang, Buqiang Xu, Zhixian Wang, Haoliang Cao, Xinle Deng, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu, Ying Wei, Guozhou Zheng, Feiyu Xiong, Haofen Wang, Huajun Chen, Ningyu Zhang
Machine Learning
Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations
Kevin Y. Li, Asher Trockman, Ananda Theertha Suresh et al. (+1 more)
Softmax
attention is the cornerstone of modern large
language models, but its
memory scales linearly and compute quadratically with sequence length. Linear recurrent models, such as linear
attention and state space models, have become widely studied as alternatives to
attention due to their linear compute and constant
memory. While these sub-quadratic
token mixing methods, or mixers, achieve promising efficiency gains and competitive results on a wide range of
benchmarks, current linear recurrent models still lag behind on tasks that require long-context
retrieval or in-context learning. A growing body of work studies hybrid architectures that attempt to mitigate these trade-offs by statically interleaving or merging
attention and recurrent blocks. In this work, we explore a new axis of developing hybrid models: across the
token sequence. We propose Oryx, a hybrid model that can, throughout a sequence, flexibly switch between different mixers, for example quadratic
attention for rich context utilization and linear recurrences for efficient generation. Oryx ties at least 90% of its parameters across mixers, enabling
attention and recurrent modes to operate over shared internal representations. We validate our design with Mamba-2 and Gated DeltaNet variants, up to 1.4B models. Under fixed
token budgets and a mixed-training strategy, Oryx achieves comparable or better performance than its single-mixer baselines. At the 1.4B scale, all instances of Oryx outperform their respective baselines by at least 0.7 percentage points on averaged
language modeling tasks. On
retrieval tasks, Oryx achieves performance comparable to the
Transformer baseline even when processing only a tiny fraction (<10%) of the
tokens in
attention mode. These results suggest that
attention and linear recurrent models can share internal representations, and motivate sequence-axis hybridization as a promising direction.
Read the full abstract ▾
All authors Kevin Y. Li, Asher Trockman, Ananda Theertha Suresh, Ziteng Sun
Machine Learning
Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learning
Mehryar Mohri and Yutao Zhong
Many real-world classification tasks require predicting multiple labels per instance, necessitating the optimization of complex evaluation metrics such as the $F$-measure and Jaccard index. While the Empirical Utility Maximization (EUM) framework is natural for these population-level metrics, existing theoretical results are largely limited to asymptotic Bayes-consistency. In this paper, we develop principled learning
algorithms for optimizing a broad class of generalized metrics within the EUM framework, grounded in the stronger notion of $H$-consistency. Our key contribution is the design of novel surrogate loss functions for multi-label learning that admit provable $H$-consistency bounds, enabling optimization with non-asymptotic guarantees tailored to the hypothesis class and finite samples. Crucially, we prove these combinatorially formulated surrogates decompose exactly, operating in strictly $O(l)$ time without approximations. Building on this foundation, we introduce MMO (Multi-Label Metric Optimization), a new family of
algorithms for optimizing generalized linear-fractional metrics. We validate our approach through extensive experiments, demonstrating robust scalability and superior performance over state-of-the-art continuous baselines on large-scale
datasets (MS-COCO, Reuters-21578) in high-sparsity, deep learning regimes. Our results offer both theoretical rigor and practical effectiveness for general multi-label metric optimization.
Read the full abstract ▾
Machine Learning
Inference-Native Zeroth-Order Optimization for LLMs
Zelin Li and Caiwen Ding
Zeroth-order (ZO) methods train large
language models using only forward passes, yet common ZO execution paths perform substantial work beyond what the
algorithm itself requires. To remove this extra execution overhead, we present Infer-ZO, which separates the evaluations required by the
algorithm from how they are executed, allowing them to reuse existing inference-engine optimizations. After removing inherited execution work, a complete Infer-ZO step on Qwen3-14B adds only 1.16% wall-clock time over matched inference, bringing ZO execution close to its fundamental inference workload. With Infer-ZO, ZO evaluations run at near-inference cost with frozen base weights and can share GPU batches with ordinary inference requests. In co-serving experiments, foreground and background throughput remain within 1-3% of the corresponding background-request baseline. Across 15 Qwen3, Llama, and OPT models, Infer-ZO achieves 2.10x-9.94x end-to-end step speedups over released LoZO. Code is available at https://github.com/playeriv65/zo-vllm.
Read the full abstract ▾
Machine Learning
Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL
Kunhao Zheng, Pierre Chambon, Juliette Decugis et al. (+4 more)
Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between competing objectives, but whether extrapolative weight averaging can extend such frontiers to new checkpoints useful at inference time, without additional RL training, remains unclear. We study this question in RL for competitive programming, where hidden unit tests under time and
memory limits enforce both functional correctness and computational efficiency. Starting from a shared initialization, we train checkpoints under nested unit-test coverage: low-coverage rewards require passing smaller-input tests, while high-coverage rewards require passing progressively larger tests up to the full suite. This sweep reveals the emergence of a correctness-efficiency frontier: on hard problems, higher-coverage reward reduces optimization failures but increases correctness failures, leaving solve rate nearly unchanged. Interpolation between low- and high-coverage checkpoints recovers this frontier, while extrapolation extends it beyond the trained endpoints. Both the frontier and its extrapolative continuation appear across three inference settings, pure
reasoning, tool use, and agentic coding, and across two model scales, 32B and 7B. At the problem level, moving along the frontier changes which problems are solved, making extrapolated checkpoints complementary policies in inference-time scaling. Ensembles with extrapolative weight averaging broaden coverage and improve pass@250 on LCB/hard by 3.3% over the best single checkpoint at matched sample budget. These results show that nested unit-test coverage in code RL induces a frontier that extrapolative weight averaging can navigate, extend, and exploit.
Read the full abstract ▾
All authors Kunhao Zheng, Pierre Chambon, Juliette Decugis, Jonas Gehring, Taco Cohen, Benjamin Negrevergne, Gabriel Synnaeve
Machine Learning
BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks
Tirtharaj Dash
Tabular data in knowledge-rich domains often carries a latent prior in the form of Boolean implication relationships (BIRs) between pairs of features. We mine such relationships with a sparse-exception binomial test. We encode the resulting typed graph as the connectivity of a layered neural network, called BIRDNet, in which each hidden unit corresponds to one mined rule and binds only to its two features. We show two consequences of this design: First, the architecture is sparse: at most $2/d$ of the weights in each BIR layer are active, where $d$ is the input dimension. Second, the model is intrinsically interpretable: every trained unit keeps a stable symbolic identity, so rules can be read off the network without surrogate models. Unlike most neurosymbolic models, BIRDNet does not consume an external rule base; its structural prior is mined from the data. We evaluate BIRDNet on six transcriptomic and proteomic
benchmarks. Our results show that BIRDNet stays within $0.02$ AUROC of the strongest dense baseline, while using up to $95\times$ fewer active parameters than an architecture-matched dense MLP. First-layer rules align with known biological signatures across multiple cancer subtypes and tissue types. Matched-
topology controls show that the mined graph contributes symbolic meaning rather than predictive advantage: shuffled or random pairings match or improve AUROC but no longer correspond to mined implications. Data and code are available at: https://github.com/MAHI-Group/BIRDNet.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests
Richard J. Young and Gregory D. Moody
A general-purpose
language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written. This asymmetry in the severity of a single act of compliance implies coding-specialized models should clear a higher refusal bar than general-purpose chat models, not a lower one, yet the field cannot tell whether they do. Refusal
benchmarks for malicious code are fragmented: they mix requests for executable software with requests for harmful security knowledge and report refusal rates over non-comparable corpora. This paper's central result is that the CODE-versus-KNOWLEDGE classification axis established in a prior four-corpus release remains stable under a substantially expanded corpus pool and an independently refreshed judge panel, evidence that it measures a real construct rather than an artifact of the
prompts or judges. Eight corpora spanning diverse elicitation paradigms (direct, jailbreak-decorated, indirect, and
agent/interpreter: ASTRA, CySecBench, AdvBench/harmful_behaviors, JailbreakBench, MalwareBench, RedCode, RMCBench, Scam2
Prompt) are classified under a five-judge consensus protocol (6,675
prompts x 5 judges = 33,375 calls), reaching Fleiss' kappa = 0.767 [95% CI 0.755, 0.777] ("substantial"). Critically, the panel shares no judge with the prior release (five paid commercial APIs replaced by five open-weight models from five vendors), yet the two panels agree on 94.45% of the 3,133 shared
prompts and reach Cohen's kappa = 0.952 [0.942, 0.963] on the 3,031-
prompt binary overlap: the axis survives near-total panel replacement. The released bank comprises 4,748 consensus-CODE and 1,923 consensus-KNOWLEDGE
prompts, a reliability-quantified
benchmark whose central classification axis is shown stable across corpus expansion and judge-panel replacement.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
Xinle Deng, Ruobin Zhong, Hujin Peng et al. (+15 more)
Memory is essential for enabling large
language models to support long-horizon
reasoning, yet existing
memory systems remain unreliable and difficult to debug. Tracing
memory's dynamic
evolution is crucial to understand how information is synthesized, propagated, or corrupted over time. In this work, we study the new problem of error tracing and attribution in LLM
memory systems. We propose a novel framework that transforms
memory pipelines into executable
memory evolution graphs, enabling fine-grained tracing of operational information flow. We then construct MemTraceBench, a
benchmark collected from representative
memory systems such as Long-Context, RAG, Mem0, and EverMemOS, to systematically study
memory failure modes. We further introduce an automatic attribution method that iteratively traces operation subgraphs to pinpoint the root cause of any failed case. Our analysis reveals that
memory failures are systematic, stemming from operation-level issues like information loss and
retrieval misalignment. Crucially, we leverage these fine-grained attribution signals to guide downstream
prompt optimization, establishing a closed-loop system that automatically corrects faults and boosts end-task performance by up to 7.62 percentage points. Code has ben released at https://github.com/zjunlp/MemTrace.
Read the full abstract ▾
All authors Xinle Deng, Ruobin Zhong, Hujin Peng, Xiaoben Lu, Yanzhe Wu, Guang Li, Buqiang Xu, Yunzhi Yao, Jizhan Fang, Haoliang Cao, Junjie Guo, Yuan Yuan, Ziqing Ma, Yuanqiang Yu, Rui Hu, Baohua Dong, Hangcheng Zhu, Ningyu Zhang
Machine Learning · Cross-listed from stat.ML
Beyond Lipschitz: Data-Driven Robustness via Discrete Modulus of Continuity
Jürgen Dölz, Michael Multerer and Michele Palma
Robustness of neural networks is commonly quantified via local or global Lipschitz constants. However, Lipschitz continuity can be overly coarse or overly restrictive as global robustness measure, failing to capture nuanced, data-dependent behavior. We propose a data-driven, architecture-agnostic framework based on the discrete modulus of continuity (DMOC), a non linear generalization of Lipschitz continuity that provides a finer notion of robustness. Unlike many existing approaches, DMOC does not require access to model internals and instead evaluates regularity relative to the data distribution. This shifts the focus from the model to the data, which provide a data-driven baseline of regularity against which the network's robustness is assessed. We establish convergence results for DMOC-induced seminorms with explicit data-driven rates in terms of the separation distance, and introduce a scalable minibatch
algorithm that reduces the quadratic cost of exact computation, enabling application to large-scale data sets such as ImageNet. Empirically, DMOC serves as an architecture independent diagnostic: it distinguishes trained from untrained networks, reveals underfitting and overfitting regimes, and yields, as a special case, tight Lipschitz estimates comparable to state-of-the-art method such as ECLipsE and ECLipsE-fast.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures
Krishnam Gupta
We discover that VLA architectures fail in fundamentally different, predictable ways at the motor-command level. Running VQ-BeT,
Diffusion Policy, and ACT on identical evaluation protocols (n=450 episodes across PushT and ALOHA 14-DOF bimanual manipulation), we find: (1) direction reversal rate is a universal failure predictor across all three architectures (AUROC=0.93, 0.79, 0.91; p<0.001); (2) jerk monitoring is predictive only for discrete-
token architectures, following a discrete-to-continuous gradient (0.88, 0.69, 0.41); (3) velocity violations alone are non-predictive everywhere (AUROC 0.41-0.69), yet velocity checking is the most common safety mechanism in VLA deployment code; and (4) for continuous-family VLAs, velocity monitoring provides effectively zero predictive signal (AUROC=0.52 on ACT, 0.41 on
Diffusion), proving that architecture-matched monitor selection is essential. These results quantify a monitoring consequence of the well-known discrete/continuous VLA distinction: the two families produce qualitatively different failure signatures that require different monitors. No single monitor works universally; architecture-matched selection is required. This finding was enabled by SafeContract, a training-free, black-box action monitoring toolkit with conformal calibration. Code: https://github.com/krishnam94/vla-edge
Read the full abstract ▾