Artificial Intelligence · Cross-listed from cs.LG
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
Changyue Li, Jiaming He, Youliang Yuan et al. (+4 more)
Fine-Tuning-as-a-Service (FTaaS) platforms let users perform supervised fine-tuning (SFT) on customized data, but this pipeline can erode model safety
alignment. To recover safety without re-running full
alignment, existing realignment methods focus on calibrating the integration of safety patches into fine-tuned models. These methods exhibit a persistent safety-utility trade-off: weak repair leaves harmful behavior intact, while stronger repair increasingly damages the benign task. This paper shifts the focus from online calibration to offline patch learning and aims to learn a safety patch that restores safety while preserving task-specific capabilities. To this end, we propose TRACE, which simulates harmful SFT trajectories to produce progressively corrupted model states, and optimizes a safety patch simultaneously across these states. TRACE trains the safety patch during the offline stage, and reuses it across all user checkpoints without per-user calibration. We evaluate two representative models using three harmful SFT
datasets, together with three utility
benchmarks. Across six
benchmarks and two models, TRACE consistently dominates the safety-utility frontier. TRACE improves the safety rate by up to 77 percentage points over the best baselines, while maintaining comparable utility to the undefended fine-tuned model.
Read the full abstract ▾
All authors Changyue Li, Jiaming He, Youliang Yuan, Jialin Wu, Boxi Yu, Zhicong Huang, Pinjia He
Artificial Intelligence · Cross-listed from cs.LG
KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?
Yunxiang Zhang, Ping Yu, Jianyu Wang et al. (+4 more)
Recent large
language models (LLMs) can generate custom CUDA kernels that appear to outperform PyTorch on
benchmarks such as KernelBench. Building upon this foundational framework, we demonstrate that frontier models frequently engage in reward hacking to artificially inflate reported performance. In this work, we identify two areas where evaluation frameworks must co-evolve with model capabilities. First, to accurately measure true speedup, we examine the baseline timing mechanism, noting that enabling Tensor Core acceleration with TF32 provides a more realistic estimation of execution on modern GPUs. Second, concerning algorithmic correctness, models often exploit the narrow test distribution by hardcoding bypasses for specific tensor values. By skipping required computations, these kernels artificially accelerate execution rather than implementing actual CUDA kernels. We introduce KernelBench-Verified, an extended evaluation framework that incorporates a TF32-enabled baseline and a four-distribution hidden test suite. We additionally introduce
memory efficiency metrics that capture the often-overlooked speed-
memory tradeoff in kernel optimization. Under verified single-turn evaluation with seven frontier LLMs, we find that the best-performing model (GPT-5.5) achieves a 0.88x
geometric mean speedup, significantly lower than the 1.43x speedup observed under the standard evaluation protocol. No model consistently outperforms PyTorch when evaluated against realistic baselines. On the
memory front, 28% of GPU kernels generated by the best model increase peak GPU
memory usage. Our findings demonstrate the necessity of continually adapting robust evaluation protocols as LLM kernel generation capabilities advance.
Read the full abstract ▾
All authors Yunxiang Zhang, Ping Yu, Jianyu Wang, Max Fan, Julian Reed, Azalia Mirhoseini, Will Su
Artificial Intelligence · Cross-listed from cs.LG
Normalized Rewards for Preference Optimization
Shawn Im, Federico Danieli, Skyler Seto et al. (+2 more)
Direct
Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences. However, DAAs have been observed to over-optimize their implicit reward model and decrease the likelihood of preferred responses. This results in a decrease in the total likelihood assigned to responses seen in the preference
dataset, potentially resulting in undesirable behavior. To counteract this undesired side-effect of DAAs, we examine the effect of using objectives that add a regularization term to maintain the total length-normalized probabilities of the chosen and rejected responses. To better understand over-optimization, we investigate how response likelihood changes are distributed over the
tokens with and without regularization. We find that a significant portion of the likelihood changes are due to a small set of outlier
tokens, which explains how DAAs improve generation quality despite decreasing the likelihoods of chosen responses. We apply the proposed regularization to reference-based (DPO) and reference-free (SimPO) methods and find (1) improved trade-offs between generation quality and general
benchmark capability and (2) improvements in reward modeling across
datasets. For example, on Llama-3.1-8B-Instruct, we see both a >20% relative increase in AlpacaEval2 scores and >9% relative performance gains on general
benchmarks. Additionally, we find that the added regularization term effectively mitigates the amount of displacement within preferred responses overall, and for the outlier
tokens specifically, by utilizing low-likelihood
tokens.
Read the full abstract ▾
All authors Shawn Im, Federico Danieli, Skyler Seto, Barry-John Theobald, Katherine Metcalf
Artificial Intelligence · Cross-listed from cs.DL
When AI Classifies: What Counts as Public Administration?
Shaoming Cheng and Laurie Schintler
This study examines how alternative systems of scholarly representation identify and characterize broad public administration (PA) and artificial intelligence related public administration (AI-in-PA) scholarship. Using Web of Science and OpenAlex, it compares five approaches based on author-defined, citation-driven, and AI-assisted representations. The results highlight substantial differences in corpus size, publication types, publishing outlets, temporal development, and thematic clustering and structure. The alternative approaches often identify different knowledge domains instead of varied subsets of the same scholarship and therefore produce distinct representations, as evidenced by no overlap in publications and publishing outlets across representations. The findings suggest that algorithmic knowledge organization increasingly influences how interdisciplinary scholarship is classified, structured, and understood and, epistemologically, how its visibility, intellectual structure, and boundaries are represented. AI-enabled scholarly classifications and representations are not neutral but interpretative, likely self-reinforcing, and potentially constrain the
evolution and adaptation of disciplinary boundaries. Human disciplinary judgment is essential and is complemented rather than replaced.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IT
Contrastive Predictive Coding with Compression for Enhanced Channel State Feedback in Wireless Networks
Ahmed Y. Radwan, Fahad Syed Muhammad, Matthew Baker et al. (+1 more)
Accurate and timely channel state information (CSI) is essential for next-generation wireless systems, yet existing works treat CSI compression and CSI prediction as separate problems, both in academia and in current 3GPP studies. Consequently, channel aging remains insufficiently addressed within standardized CSI feedback pipelines. In this article, we propose a unified compression-prediction framework that integrates Contrastive Predictive Coding (CPC) directly into the 3GPP-compliant CSI compression architecture. Instead of predicting high-dimensional CSI
matrices, our approach forecasts future latent representations and jointly optimizes reconstruction fidelity and temporal predictive coherence via a combined 1-SGCS and InfoNCE objective. This design enables temporal representation learning without increasing feedback overhead. We present two variants: CPC-before-Compression, which performs autoregressive modeling on encoded features prior to quantization, and CPC-after-Compression, which shifts temporal modeling to the base-station to reduce the complexity of users' devices. Evaluations on 3GPP-compliant
datasets from Nokia, Oppo, and CATT show that CPC-before-Compression achieves over 90% reconstruction accuracy with 32x lower decoder GFLOPs than the 3GPP baseline, while CPC-after-Compression preserves an identical encoder footprint and the same 64-bit feedback overhead. By unifying compression and prediction within a standardized pipeline, the proposed framework provides an age-aware, computationally efficient CSI feedback solution. The source code is publicly available at: https://github.com/AhmedRadwan02/cpc-3gpp
Read the full abstract ▾
All authors Ahmed Y. Radwan, Fahad Syed Muhammad, Matthew Baker, Hina Tabassum
Artificial Intelligence · Cross-listed from cs.CV
DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences
Yankai Yang, Yancheng Long, Bin Wen et al. (+4 more)
Video multimodal large
language models have made strong progress on open-ended
video understanding, but they still lack precise local spatiotemporal perception. When two
videos share almost the same global semantics and differ only in a short time span or a small region, current models often fail to find the change and provide reliable evidence. We propose DELTAVID, a verifiable proxy-task framework that enhances fine-grained spatiotemporal perception with cross-
video differences. The key idea is to turn cross-
video spot-the-difference into a trainable perception signal, where a model identifies local changes, judges temporal boundaries, and organizes spatial evidence by comparing similar
videos. To make this signal scalable to train and reliable to evaluate, we further introduce DELTAVID-10K and DELTAVID-Bench, which convert controllable local differences in real
videos into evidence-labeled training and test samples. Experiments show that DELTAVID substantially improves performance on cross-
video difference understanding and transfers the learned local evidence ability to general
video understanding
benchmarks, including MMVU, MLVU,
Video-MME, VideoHolmes, VideoMMMU, LVBench, TempCompass, and LongVideoBench. These results show that cross-
video differences are not only an effective way to diagnose fine-grained perception failures, but also a scalable proxy supervision that moves
Video MLLMs from coarse semantic understanding toward fine-grained spatiotemporal evidence
reasoning.
Read the full abstract ▾
All authors Yankai Yang, Yancheng Long, Bin Wen, Fan Yang, Tingting Gao, Han Li, Shuo Yang
Artificial Intelligence · Cross-listed from cs.RO
Locker-based Truck-Drone Routing with Integrated Considerations of Pickups, Deliveries, and No-Fly Zones
Xuanyu Liu, Hui Hu, Jiao Zhao et al. (+2 more)
Truck-drone delivery is an emerging last-mile logistics mode combining the long-haul capacity of trucks with the flexible service capability of drones. In locker-based operations, smart lockers serve not only as temporary parcel storage facilities but also as automated drone docking and service nodes. These automated nodes support drone takeoff, landing, parcel handover, and battery replacement, thereby significantly extending the service range and operational flexibility of drone-assisted delivery networks. However, practical locker-based delivery systems face complex real-world challenges, requiring the integrated coordination of not only parcel delivery, return pickup, battery-constrained and load-dependent drone flights, but also necessary detours around restricted airspace. To address this practical and multifaceted challenge, this paper introduces a locker-based truck-drone routing problem with integrated considerations of pickups, deliveries, and no-fly zones (LTDRP-PDNF), with the objective of minimizing the total operational cost of a fleet of drone-equipped trucks. We formulate the route construction process as a Markov Decision Process and develop a two-stage deep reinforcement learning-based neural heuristic. The first stage utilizes an
attention-based encoder and a Bidirectional Gated Recurrent Unit decoder to solve the truck-only routing problem, formulated as a capacitated vehicle routing problem. The second stage combines a policy-transfer strategy with a hybrid dispatch assignment heuristic to construct fully coordinated truck and drone routes for LTDRP-PDNF. Experiments on instances of different scales demonstrate that the proposed method outperforms metaheuristic and neural heuristic baselines in most cases while maintaining exceptionally short computation times, offering an effective, scalable solution framework under practical operational constraints.
Read the full abstract ▾
All authors Xuanyu Liu, Hui Hu, Jiao Zhao, Ziliang Wang, Zhengbing He
Artificial Intelligence · Cross-listed from eess.AS
Listening Between the Lines: Joint Learning of ASR Embeddings and LLM-Augmented Linguistics for Dementia Detection
Olivier Jiyoun Jung, Jonghyeon Park and Myungwoo Oh
Early detection of dementia through
speech analysis offers a non-invasive screening alternative, but capturing both acoustic and linguistic biomarkers remains challenging. We propose a
multimodal framework leveraging Whisper for dual-purpose extraction: acoustic representations from encoder outputs and transcripts via automatic
speech recognition (ASR). For the acoustic pathway, temporal networks with
attention pooling aggregate variable-length sequences into fixed-dimensional
embeddings. For the linguistic pathway, we
prompt a large
language model (LLM) to extract interpretable features spanning lexical diversity, syntactic complexity, semantic coherence, and discourse patterns. A gated fusion network integrates both modalities. On ADReSS and ADReSSo, our method achieves F1-scores of 89.47% and 90.14%, demonstrating effective integration of acoustic and LLM-augmented linguistic features. Ablation shows that
multimodal fusion consistently outperforms either modality alone.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration
Thiru Thillai Nadarasar Bahavan, Sachith Seneviratne and Saman Halgamuge
Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods. This manifests itself as either overconfident incorrect predictions or under-confident correct predictions. Label smoothing (LS) enhances model calibration by introducing
entropy regularization during training through redistributing probability mass from the ground-truth label to the remaining classes. LS, including Margin-based LS (MbLS), have restrictive assumptions: they rely on predefined, uniform smoothing rules and only tackle overconfidence. In reality, samples exhibit diverse characteristics, such as difficulty/ambiguity, that interact with the evolving nature of the model being trained. In training, samples may have various degrees of under- or overconfidence. To overcome this, a mechanism that identifies the specific confidence state of each sample and determines the appropriate degree of smoothing in each training step is needed, tailoring the adjustment to the individual sample. We propose FedLAS: Feature-Modulated Bidirectional Label Smoothing, a plug-and-play
algorithm for label smoothing-based losses. In FedLAS, we introduce a Feature Norm-based Confidence Indicator (NCI) to control smoothing and a Bidirectional Calibration Gating (BCG) module to detect both over and under-confidence. Our
algorithm can be integrated with LS and MbLS based losses when applied to standard DNNs, enhancing performance. Extensive experiments on standard and fine-grained high-resolution
vision benchmarks show that FedLAS consistently improves calibration compared to modern baselines, reducing Expected Calibration Error (ECE) and Adaptive ECE while maintaining Top-1 accuracy. Code: github.com/nadarasarbahavan/FEDLAS
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots
Nima Dorzhiev
We present RIPA, the first systematic multi-channel empirical study of
prompt injection attacks delivered through the sensory pipeline of a ROS 2-based LLM-controlled robotic system. Across 100 independent runs per injection variant on five LLMs spanning four model families and parameter scales from approximately 4B to approximately 284B (DeepSeek-V4-Flash, Llama-3-8B-Instruct-Lite, Llama-3.3-70B-Instruct-Turbo, Qwen 2.5-7B-Instruct-Turbo, Gemma-3n-E4B), we identify model-specific vulnerability profiles that do not follow a monotonic scaling trend: Llama-3.3-70B-Instruct-Turbo exhibits 100% attack success rate (ASR) across all injection variants, while Llama-3-8B-Instruct-Lite and Qwen 2.5-7B-Instruct-Turbo resist direct-override injection (0% ASR), and the smallest model evaluated (Gemma-3n-E4B, approximately 4B) matches the 70B model's vulnerability profile, indicating that robustness is model-specific rather than scale-dependent. We propose a hybrid semantic firewall that achieves 0% ASR against known injection patterns with no false positives on a preliminary benign set (0/20 commands) but exhibits a 10.2% trial-weighted bypass rate (58/570 trials; N equals 30 per payload across 19 obfuscation payloads) against adversarially obfuscated attacks, exposing a critical gap between rule-based and semantic defense layers. We further introduce three sensory injection channels: visual (Channel 1, via OCR), audio (Channel 2, via Whisper STT), and
LiDAR sensor context poisoning (Channel 3). We show that Channel 3, which injects fabricated obstacle data into the
robot environment-state representation at the LLM system-
prompt level, achieves 100% ASR across all variants on DeepSeek-V4-Flash. We also contribute a firewall bypass taxonomy spanning 19 obfuscation payloads across five categories. All code, data, and results are publicly available.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.NE
Analysis of Parameter Settings for the Bat Algorithm Using Variance Evolution
Xin-She Yang and Mehmet Karamanoglu
Parameter settings in evolutionary
algorithms and metaheuristics are important because such parameter values can influence the performance of
algorithms under evaluation. For a given
algorithm, there are many different numerical experiments to show that the
algorithm can work well in practice; however, in most cases there is no theoretical analysis of parameter settings. In this work, we show that theoretical analysis using the theory of dynamical systems and
evolution of population variance can give some good results in terms of parameter ranges for the bat
algorithm. We also show that results from numerical experiments are consistent with theoretical bounds. Such analyses can provide good insights from different perspectives about the algorithmic characteristics such as variance
evolution, transition between exploration and exploitation as well as convergence behaviour.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LO
Algorithmic Unverifiability of Safety for Fixed and Recursively Self-Improving Systems
Jose Pascual Gumbau Mezquita
Existing impossibility results for AI verification concern a fixed system. Self-modifying systems (
agents that rewrite their own code, recursive self-improvement loops) raise a different question: can a safety property that holds now be certified, in advance, to keep holding after the system rewrites itself? We model one step of self-modification as a total computable transformation of code, and preservation as 'safe now and safe after the step'. If the transformation depends only on behaviour, preservation is Rice's
theorem one level up; if it reads the code, as self-modification does, preservation is no longer semantic, yet at least as hard as the halting problem, by the same s-m-n reduction carried out inside a class of behaviourally identical programs. One step is never harder than the property; persistence along the whole trajectory can be one arithmetical level higher. No tower of supervisors lowers the problem; every total supervisor errs on a set of systems it cannot locate. Every faithful scheme certifying on finite behavioural evidence admits, for properties not settled by any finite set of inputs, an
evolution trace it certifies at every stage while the property is violated. Statically, we record the classical limits (Rice, Goedel, Trakhtenbrot) and add the resource face: over succinctly described finite environments, verifying a policy against an adversary is coNP-complete and synthesising one PSPACE-complete. These limits do not say self-modifying systems are unsafe; they locate where algorithmic guarantees break, at the expressivity a general system needs: Turing-completeness and unrestricted self-modification. What survives is exact: a monitor detects the first violation of a safety property, and no sound procedure certifies all safe systems; certification requires restricting rewrites by design; and a frozen reference keeps the question well posed.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs
Nhi Nguyen, Shauli Ravfogel and Rajesh Ranganath
Large
language models (LLMs) are increasingly deployed in high-stakes domains, where free-text explanations such as chain-of-thought and post-hoc rationales are used to justify model outputs. Yet it remains unclear whether these explanations are sufficient, i.e., if they contain enough information to explain the model's output-generating process. We generalize classical sufficiency from feature attributions to arbitrary explanations and prove that explanation sufficiency can change depending on the input distribution, which must be explicitly defined for LLM explanations. We propose using the LLM itself to generate alternative inputs conditioned on an explanation, capturing its beliefs about possible inputs. We formalize self-consistent sufficiency as a goal for free-text explanations and introduce an information-theoretic metric, SCSuff, that enables evaluation of free-text explanations without relying on predefined biases or shortcuts. Our experiments show that SCSuff agrees with targeted perturbation tests where applicable and demonstrate that explanation sufficiency can vary with the input distribution. We find LLM explanations are generally insufficient and weakly correlated with model size, accuracy, or output
entropy. Analysis of final-
token hidden states shows that top and bottom SCSuff scores can be predicted from internal representations, suggesting that SCSuff can guide detection and improvement of sufficient LLM explanations. The code for this paper is available at https://github.com/rajesh-lab/self-consistent-sufficiency .
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Fast and Accurate Outlier-Aware LiDAR Super-Resolution for SLAM Applications
Christos Anagnostopoulos, Alexandros Gkillas, Nikos Piperigkos et al. (+1 more)
This work tackles the challenge of enhancing low-resolution
LiDAR sensors for SLAM applications through a novel Deep Unrolling-based Super-Resolution (SR) model. We integrate an outlier removal module to ensure structural integrity while maintaining real-time performance. By leveraging a model-based optimization approach, our method efficiently reconstructs high-resolution point clouds while minimizing computational overhead. The proposed SR model is evaluated within a
LiDAR SLAM framework, demonstrating significant improvements in pose estimation accuracy and efficiency compared to state-of-the-art SR methods.
Read the full abstract ▾
All authors Christos Anagnostopoulos, Alexandros Gkillas, Nikos Piperigkos, Aris S. Lalos
Artificial Intelligence · Cross-listed from cs.DB
Database Context Compression for Text-to-SQL on Real-World Large Databases
Jingwen Liu, Weibin Liao, Xin Gao et al. (+2 more)
Recent progress in Text-to-SQL has been driven by stronger
language models and prompting strategies, yet performance on real enterprise
benchmarks such as Spider 2.0 and BIRD remains far below that on classical academic
datasets. We argue that the main bottleneck is no longer
reasoning, but database representation. Real databases contain repeated audit columns, large groups of similar tables, opaque identifiers whose meanings are stored only in documentation, and extensive data dictionaries with little query-relevant information. Existing query-aware methods, including schema linking and
retrieval-based schema selection, filter this raw context but still operate on redundant and verbose representations. We reformulate the problem as database context compression, a query-agnostic transformation that rewrites schemas, semantic descriptions, and external documentation into a compact representation. We formalize this transformation with the SGCF (Support-Gain Component Factorization) principle, which unifies repeated column extraction, isomorphic table templating, semantic componentization, and evidence purification under a single coverage objective. Based on SGCF, we propose DBCC, a database-side middleware that performs offline structural and semantic compression together with lightweight online evidence purification. DBCC is model-agnostic and can be integrated into existing Text-to-SQL pipelines. On Spider 2.0-Snow and BIRD, DBCC reduces input context by up to two orders of magnitude (from 2.6M to 34.7K
tokens on the largest Spider 2.0-Snow subset), improves schema-linking strict recall from 0% to 56.5% under DeepSeek-V3.2 (63.1% under Claude Opus 4.7), and consistently increases end-to-end execution accuracy by 1.8-1.9% over three recent Text-to-SQL systems. Our code is open-sourced at https://github.com/MrBlankness/SchemaCompression.
Read the full abstract ▾
All authors Jingwen Liu, Weibin Liao, Xin Gao, Junfeng Zhao, Yasha Wang
Artificial Intelligence · Cross-listed from cs.NE
Neuromorphic Energy-Aware Learning for Adaptive Deep Brain Stimulation
Binh Nguyen, Colleen Josephson, Mircea Teodorescu et al. (+2 more)
Neuromorphic and edge computing research has focused on reducing the inference cost of neural network controllers, yet in physical closed-loop systems the actuator can rival or exceed an efficient controller in energy. An efficient controller is therefore necessary but not sufficient, because the actuator becomes the cost worth reducing once inference no longer dominates it. Here, we introduce energy-aware learning, an approach that incorporates actuator energy directly into the reinforcement learning reward, and demonstrate it in closed-loop deep
brain stimulation (DBS) for Parkinson's disease. A deep spiking Q-network, trained in a biophysical cortico-basal ganglia-thalamic
circuit model, learns to suppress pathological alpha-beta oscillations by 45.2% while reducing stimulation charge by 80.0% relative to continuous DBS. Sparsity-constrained knowledge
distillation compresses the policy onto the SynSense XyloAudio 3 neuromorphic processor at 0.52 mW inference power, yielding 28.1x lower energy per inference than an equivalent artificial neural network on conventional edge hardware. By co-optimizing stimulation energy and inference efficiency, the framework addresses both major power demands in implantable neuromodulation.
Read the full abstract ▾
All authors Binh Nguyen, Colleen Josephson, Mircea Teodorescu, Gert Cauwenberghs, Jason Eshraghian
Artificial Intelligence · Cross-listed from cs.CV
Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
Anya Ji, Abhijith Varma Mudunuri, David M. Chan et al. (+1 more)
While recent
vision-
language models (VLMs) have achieved significant improvements on static visual-to-code tasks such as generating code for webpages, charts, or SVGs, it remains unclear whether they can recover temporal dynamics when motion is present. To this end, we introduce Animation2Code, a
benchmark for evaluating temporal visual
reasoning via reconstructing executable web animation code from
videos. Animation2Code consists of 1,069 web animation
videos with diverse visual appearances and motion patterns, paired with corresponding HTML/CSS/JavaScript implementations. We propose two human-aligned metrics, appearance similarity and temporal similarity, which allow us to disentangle visual fidelity from temporal
alignment when comparing rendered animations against ground-truth samples. Benchmarking state-of-the-art VLMs on this
dataset shows that current VLMs struggle to maintain temporal consistency in reconstruction, even when achieving high appearance similarity, including under finetuning and iterative refinement settings. Code and data are available at https://anya-ji.github.io/animation2code-website .
Read the full abstract ▾
All authors Anya Ji, Abhijith Varma Mudunuri, David M. Chan, Alane Suhr
Artificial Intelligence
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
Tianlong Wang, Yuhang Wang, Weibin Liao et al. (+5 more)
Current approaches to enhance Large
Language Model (LLM)
reasoning, such as Chain-of-Thought and "Wait"
prompts, primarily encourage models to think more, yet often fail to guide them toward Truth. While Representation Editing (RepE) offers a intrinsic control, its application to dynamic
reasoning trajectories remains underexplored. In this work, we bridge this gap by investigating the geometry of truth within unfolding
reasoning chains. We uncover three critical insights: (1) Truth is encoded at the sentence level and is entangled with latent
reasoning patterns; (2) Effective intervention follows an Uncertainty Principle and a Decay Effect, requiring localization to early, high-
entropy forks; (3) Naive steering vectors suffer from noise, risking collateral damage to correct trajectories. Based on these findings, we propose DynaSteer, a dynamic RepE framework. DynaSteer employs pattern clustering to disentangle
reasoning manifolds and utilizes Fisher-LDA to project purified truth. By dynamically monitoring lookahead
entropy, it selectively steers and rolls back trajectories only when necessary. Comprehensive experimental results on several MATH
benchmark verify the effectiveness of DynaSteer, and experiments on out-of-domain coding tasks further confirm its generalization ability. Our code is publicly available at https://github.com/tianlwang/DynaSteer.
Read the full abstract ▾
All authors Tianlong Wang, Yuhang Wang, Weibin Liao, Xin Gao, Xinyu Ma, Yang Lin, Yasha Wang, Liantao Ma
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
Surrogate-Gated Generation and Foundation-Model Embeddings for Bayesian Materials Design
Sk Md Ahnaf Akif Alvi, Jan Janssen, Danny Perez et al. (+2 more)
Closed-loop materials discovery iterates between proposing candidate structures and evaluating their properties, and property evaluation dominates the cost. In the generative variant, a learned prior proposes candidate
crystals and a property oracle scores them; we ask whether a cheap probabilistic surrogate can triage the generator's output, and what such a surrogate must do well. Across three architecturally distinct pretrained
diffusion priors (MatterGen, CrystalFlow, ADiT) and two targets (room-temperature heat capacity and bulk modulus), we insert a Gaussian process acquisition gate between structure generation and the oracle in an RL-steered generative workflow. The gate matches or exceeds ungated fine-tuning of the generative model while capping oracle calls at a fixed per-cycle budget. Budget-matched ablations isolate the mechanism. At an identical four-call budget, ranking-based selection outperforms arbitrary selection, confirming that the gain comes from the surrogate's choice; the gate comes within $\sim$9% of exhaustive oracle spending at roughly one-fifth of the calls. A density-functional-theory check of the bulk-modulus discoveries confirms the learned oracle to within 2.5% on average and the surrogate's ranking of the generated structures at Spearman $\rho = 0.94$. A cross-factorial
benchmark of surrogate performance spanning mechanical, electronic, and vibrational properties identifies pretrained ORB
embeddings with a Gaussian process as the most reliable combination, which we adopt as the building blocks of the proposed workflow. The complete pipeline is released as open-source software.
Read the full abstract ▾
All authors Sk Md Ahnaf Akif Alvi, Jan Janssen, Danny Perez, Douglas Allaire, Raymundo Arroyave
Artificial Intelligence · Cross-listed from cs.CL
Correct codes for the wrong reasons? validating LLMs as measurement instruments for theoretical constructs
Manuel Pita
When a large
language model (LLM) codes a construct in text as a human annotator would, that agreement makes the LLM a reliable coder. Yet reliability leaves construct validity untouched. The instrument may be theory-naive, reaching the code through a correlate that meets none of the demands the construct's theory makes, and no current method tells that apart from genuine measurement. We propose grain calibration as a method that closes the gap. It decomposes a construct into clause-level components, tests each against the text with extractive evidence, and combines the results through an explicit, theory-derived rule. Because the rule is stated rather than lodged in one opaque pass, its structure is evidence about the process rather than the output. It shows which components settled a code, and, when the code is wrong, whether a component was missed or an adjacent construct mistaken for it. Validation shifts from scoring an instrument's outputs against an annotator to showing that the instrument runs on the construct its theory specifies.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings
Rodrigo Mendoza-Smith
The axiom of choice has divided the foundations of mathematics for over a century, but the distinction between classical and constructive proofs has remained a philosophical and methodological one. We use Lean 4's kernel-level tracking of axiom dependence to show that the axiom of choice has a measurable
geometric correlate in proof space that obeys a one-parameter mixture law and has operational consequences for neural
theorem provers. To do this, we partition $471{,}260$ declarations of Mathlib by transitive dependence on the axiom of choice and represent a filtered population of $42{,}355$ traced
theorems by their sequences of tactic invocations. We use the constructive proofs in this
dataset to train a self-supervised proof encoder and show that when using it to measure classical proofs, three complementary measurements (anomaly score, reconstruction loss, and density-superlevel containment) exhibit a common decline with the proof's distance from the axiom in the dependency graph, from sharp separation at the shallow boundary (AUC $0.847$ at distance $2$) to indistinguishability at distance~$9{+}$. Robustness controls show that the signature survives length, file, author, and topic controls, and replicates under full-source encoders trained on normalised proof source. Operationally, we show that on an evaluation sample of $251$ Mathlib
theorems, Lean's aesop tactic solves constructive
theorems at $13\times$ the rate of classical ones, and a neural-guided hybrid using the ReProver tactic generator compresses the gap to $5\times$. The
geometric anomaly score predicts aesop failure beyond proof length, providing an operational link between the
geometric signature and prover performance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Digitizing Coaching Intelligence: An Agentic Framework for Holistic Athlete Profiling using VLM and RAG
Deep Ghosal, Ishani Sen, Wazib Ansar et al. (+1 more)
Athlete assessment is a critical process for tracking physical progress and identifying elite talent. However, during mass recruitment drives, traditional methods rely on manual observation, which is inherently subjective and unscalable, or basic computer
vision (CV) systems limited to quantitative repetition counting. These standard approaches lack the "coaching intelligence" required to evaluate qualitative physiological markers such as form degradation, spinal articulation, and fatigue. This paper presents a novel, LLM-based hybrid agentic framework for automated, holistic athlete profiling that strictly aligns with the Sports Authority of India (SAI) assessment protocols. Orchestrated via LangGraph, our dual-pipeline architecture synthesizes the
geometric precision of CV (MediaPipe) for kinematic tracking with the semantic
reasoning of
Vision-
Language Models (Llama-4-scout). To overcome the latency and
token constraints associated with
multimodal video processing, we introduce a 3 X 3 "Smart Grid" temporal chunking strategy, reducing computational overhead by over 88% while preserving critical temporal continuity. To ensure data integrity and mitigate
hallucination, the framework pioneers an autonomous "LLM-as-a-Judge" self-correction loop that cross-references quantitative and qualitative metrics before persistence. Finally, we implement a dual-persistence
Retrieval-Augmented Generation (RAG) pipeline utilizing a vector search engine (ChromaDB). This enables coaches to bypass rigid SQL databases and perform complex semantic queries (e.g., "Identify athletes with high endurance but poor core
rigidity") using natural
language. Experimental results demonstrate that this multi-
agent approach significantly bridges the gap between raw biometric tracking and actionable coaching insights, offering a scalable, objective solution for national talent identification.
Read the full abstract ▾
All authors Deep Ghosal, Ishani Sen, Wazib Ansar, Amlan Chakrabarti
Artificial Intelligence · Cross-listed from cs.PF
KernelSight-LM: A Kernel-Level LLM Inference Simulator
Xiteng Yao, Taeho Kim, Hengzhi Pei et al. (+7 more)
As large
language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets. However, the end-to-end behavior of LLMs couples serving-layer policies with low-level GPU kernel execution and rapidly evolving architectures, forcing slow, deployment-specific benchmarking that is hard to generalize. We present KernelSight-LM, a fine-grained inference simulator that models
token-level execution and produces kernel-level latency breakdowns. It decomposes each serving step into a roofline kernel model with a learned efficiency term, a communication model, and a host-overhead model, composed through a discrete-event scheduler that also captures mechanisms like prefix caching and continuous batching. KernelSight-LM offers two prediction tiers that trade target-GPU data for accuracy. The cross-generation tier uses no target-GPU measurements, only hardware specifications and kernel microbenchmarks from previously profiled GPUs, and predicts per-kernel latency on an unseen GPU generation to 12.1% error, a 1.8x improvement over the roofline baseline (22.0%). A second target-measured tier adds one model-agnostic kernel-microbenchmark sweep on the target GPU, sharpening per-kernel error to 3.8%, a 7.3x improvement over a comparable baseline (27.7%). Both tiers require far less target-GPU data than the prior systems they extend. In our simulator, these predictions yield end-to-end median (p50) errors across six model families of 15.4%, 12.8%, and 3.0% (TTFT, TPOT, throughput) in the cross-generation tier and 14.3%, 6.2%, and 2.7% in the target-measured tier, matching dedicated profiling tools while collecting far less on-device data. Beyond prediction, its kernel-level bottleneck breakdowns support hardware/software co-design and capacity planning.
Read the full abstract ▾
All authors Xiteng Yao, Taeho Kim, Hengzhi Pei, Xinle Liu, Kyle Ulrich, Leonard Lausen, Ashish Khetan, Xiang Song, George Karypis, Martin Herbordt
Artificial Intelligence
IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations
Maria Xenochristou, Ashutosh Joshi, Korosh Vatanparvar et al. (+10 more)
Recent advances in large
language models and
vision-
language models have enabled
reasoning over
multimodal data, offering opportunities for clinical applications such as decision support and triaging. However, existing medical AI
benchmarks are fragmented: some support multi-turn dialogues but lack images, while others provide
multimodal inputs but focus on single-turn QA tasks. To address this gap, we introduce IMCBench, an image-grounded, multi-turn medical conversation
benchmark that pairs real, publicly available clinical images with synthetic patient profiles to simulate realistic patient-clinician interactions. Each conversation is evaluated across three clinical dimensions: safety, accuracy, and appropriate use of uncertainty in diagnosis. We
benchmark eight
multimodal frontier models across four model families (Claude, GPT, Nova, and Llama), scoring each on a 1-5 scale using LLM-as-Jury scoring calibrated against expert clinician annotations. Our results show that Claude Opus 4.6 achieves the highest overall score (3.61), followed by Claude Sonnet 4.6 (3.30) and GPT-5.2 (3.29), though no model dominates all dimensions and safety degrades for both malignant and rare conditions ($\Delta$ = -0.27 each). Ablation studies further reveal that both visual input and EHR context contribute to safe guidance (safety drops of 0.18 and 0.23 on average when each is removed), with stronger models leveraging visual features more effectively. Together, these findings demonstrate that accurate clinical description does not guarantee safe patient guidance, motivating the need for multi-dimensional evaluation frameworks in medical AI.
Read the full abstract ▾
All authors Maria Xenochristou, Ashutosh Joshi, Korosh Vatanparvar, Mohammad Abuzar Hashemi, Prasad Kasu, Deepak Bansal, Anchal Nema, Nivedita Wadhwa, Prashams S Jain, Rebecca Abraham, Will Kimbrough, Dilek Hakkani-Tur, Wilko Schulz-Mahlendorf
Artificial Intelligence · Cross-listed from cs.CV
MammoFlow: Multiview Mammogram Synthesis with Anatomically Consistent Flow Matching
Yuexi Du, Leya Barrientos, Laura Sheiman et al. (+3 more)
Multiview mammography relies on paired craniocaudal (CC) and mediolateral oblique (MLO) views to provide complementary projections of a 3D breast volume, enabling precise anomaly localization. However, acquiring high-quality, balanced
datasets remains challenging for deep learning applications. We propose a novel method to synthesize multiview mammograms by leveraging the inherent
geometric relationship between CC and MLO views. To enforce an implicit 3D consistency prior during generation, we develop an
alignment module that searches a 2D affine transformation subspace to establish optimal anatomical correspondence. Leveraging this
alignment, we introduce a pixel-space self-consistency loss based on the Earth Mover's Distance (EMD) between the 1D anteroposterior (AP) axis tissue distributions of the generated images. Integrated into a pretrained flow matching model, MammoFlow forces synthesized pairs to share physically plausible tissue distributions from the chest wall to the nipple. To our knowledge, this is the first work to guide multiview mammogram generation using implicit
geometric tissue correspondence. Our method demonstrates superior image quality, passes expert radiologist evaluation, and generates physically consistent pairs that improve downstream classification AUC by 5%. Code is available at https://github.com/XYPB/MammoFlow
Read the full abstract ▾
All authors Yuexi Du, Leya Barrientos, Laura Sheiman, John Lewin, Hemant D. Tagare, Nicha C. Dvornek
Artificial Intelligence · Cross-listed from cs.IR
CMSL: Constructive Multi-Sequence Learning for Recommendation Systems
Zikun Cui, Renzhi Wu, Junjie Yang et al. (+10 more)
Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) by capturing the temporal nuances of user behavior. However, current state-of-the-art architectures operate under a limiting analogy: they treat user history as a monolithic chronological sequence like a sentence in a Large
Language Model (LLM). We observe a fundamental divergence between natural
language and recommendation data: unlike the linear, logical flow of text, user history is inherently multi-faceted. A user's journey is a fragmented reflection of diverse interests, resulting in much weaker coherence between items than is found in LLM training data. This lack of structural unity leads to context pollution. In single-sequence modeling, unrelated behaviors compete for the same
attention budget. This "noisy" signal dilutes the model's focus, effectively capping its ability to discern high-intent patterns from background activity. To address this, we propose Constructive Multi-Sequence Learning (CMSL), a paradigm shift from passive sequence ingestion to active "context engineering" that constructs multiple coherent sequences in latent space. CMSL leverages a learnable Sequence Construction Module to disentangle user history into "pure" thematic strands, followed by a linear
attention mechanism to efficiently model these strands at scale. CMSL has been deployed across ranking and
retrieval tasks and across four major surfaces at Meta.
Read the full abstract ▾
All authors Zikun Cui, Renzhi Wu, Junjie Yang, Li Sheng, Jijie Wei, Linfeng Liu, Tai Guo, Tao Jia, Xiaodong Wang, Hong Li, Li Yu, Sri Reddy, Hong Yan
Artificial Intelligence · Cross-listed from cs.RO
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
Yujin Wang, Junli Chen, Yixuan Li et al. (+4 more)
Embodied foundation models have recently been widely used to improve
robot generalization and task success rates. Previous works apply lossy efficient-inference techniques such as quantization,
pruning, and asynchronous inference, accepting small action quality degradation in exchange for lower per-inference computation cost and inter-action latency. However, unlike traditional static ML tasks,
embodied tasks involve repeated interaction with the environment, and task-level performance is determined not only by inference cost, but also by closed-loop effects unique to
embodied execution, which remain insufficiently characterized in current efficient-inference studies. In this work, we propose TISED (\underline{T}ask-level \underline{I}nference \underline{S}peedup \underline{E}ffect \underline{D}ecomposition), an analytical framework that unifies diverse lossy lightweighting inference optimization techniques and decomposes their effects on static and dynamic tasks; using it, we uncover several paradoxical effects: (1) on static tasks, optimization can sometimes lengthen end-to-end per-task completion time even as per-chunk time drops; (2) on dynamic tasks, moderate lossy lightweighting optimization can raise task success rate even above the baseline; and (3) the monotonicity and sweet-spot location of both effects can shift with hardware configuration. Together, our findings provide a new perspective on adapting inference optimization techniques to
embodied tasks. Source code: https://github.com/thu-ee-acts-lab/robotics-the-speedup-paradox.
Read the full abstract ▾
All authors Yujin Wang, Junli Chen, Yixuan Li, Shunan Dong, Huazhong Yang, Yongpan Liu, Hongyang Jia
Artificial Intelligence · Cross-listed from cs.LG
A Gravitational Interpretation of Safety Reversion under Fine-Tuning
Samuele Poppi and Nils Lukas
Safety
alignment in large
language models can degrade during post-training even when neither the data nor the objective is intentionally
adversarial.
Alignment rebound and reverse dynamics suggest that this degradation may reactivate behavior suppressed during safety
alignment. Building on these ideas, we hypothesize that ordinary non-
adversarial post-training follows a reversion direction: the activation-space displacement from the safety-aligned model toward a more permissive, earlier helpful-only state. We see that for Llama, every tested trajectory across references, tasks, and seeds exceeds a matched empirical null, while at aligned Llama and Qwen checkpoints, a vocabulary readout shows that the direction locally favors task-engaging over fixed refusal-like openings. Its
geometric expression is behaviorally informative: as post-training proceeds,
alignment with the direction and harmfulness increase together, yielding a strong descriptive correlation (Spearman r=0.958). To move beyond correlation, we test causal relevance during adaptation using objectives constructed from this coordinate. Across all tested Llama, Qwen, and Gemma settings from 3B to 14B, an optimizer-matched objective opposing positive motion reduces
geometric alignment and harmfulness relative to ordinary fine-tuning, whereas a separately stabilized objective reinforcing that motion increases both. Every model and scale exhibits the same mean block-baseline-push ordering, showing that the causal relevance of the reversion direction is not tied to one architecture or model size. Finally, we show that a standard safety-rehearsal objective, built without access to the direction, independently opposes it and cuts cumulative reversion by about 30% in Llama and Qwen.
Read the full abstract ▾
Artificial Intelligence
GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes
Amit Parekh, Sabrina McCallum, Kareem Al-Hasan et al. (+3 more)
Multimodal models are increasingly deployed to solve tasks collaboratively with humans or other artificial
agents. While existing
benchmarks show that they possess the fundamental capabilities, the various conditions that coincide when collaborating—time pressure, information asymmetry, and imperfect communication—have traditionally been studied in isolation. To address this gap, we introduce GPTNT, a
benchmark built on the cooperative
video game Keep Talking and Nobody Explodes, in which two
agents must coordinate to defuse procedurally generated bomb puzzles against a live countdown. One
agent has access to the bomb but not the instructions for defusing it; the other holds the instructions but cannot see or manipulate the bomb. Neither
agent can succeed alone: the task requires contributions from both, and is solvable only through effective, efficient communication. We remove turn-taking proxies or simplifications, instead requiring
agents to act asynchronously and communicate in real time. GPTNT is designed to expose how models collaborate versus how they perform alone: the instruction manual, the partner, or both, can optionally be withheld to surface what a model has memorised versus what it derives in the moment. We demonstrate that GPTNT poses a considerable challenge to the state-of-the-art: not one of the closed- and open-source models we test defuses a single bomb in real time, a bar that human players clear. In a range of controlled experiments, we explore where capabilities break down, identifying critical weaknesses in state tracking, efficient acting within the time budget, handling ambiguity, and error recovery. Since it runs on the real game, GPTNT benefits from procedural generation and inherits a living modding community: as models improve, the
benchmark can be evolved to remain challenging, rather than being solved once and retired.
Read the full abstract ▾
All authors Amit Parekh, Sabrina McCallum, Kareem Al-Hasan, Malvina Nikandrou, Alessandro Suglia, Ioannis Konstas
Artificial Intelligence · Cross-listed from eess.IV
HDDPM: Heteroscedastic Denoising Diffusion Probabilistic Model for Quantitative Low-Count Brain PET Recovery
Raymond Confidence and Udunna C. Anazodo
Positron emission
tomography (PET) seeks to balance diagnostic quality with ra-diation dose. Low-count PET noise is non-Gaussian, non-stationary, and spatial-ly dependent. It scales directly with local activity and is shaped by iterative recon-struction and physical corrections. Standard denoising
diffusion probabilistic models (DDPMs) ignore these PET properties. Their forward process adds iso-tropic, homoscedastic Gaussian noise to the target. Such an approach fails to cap-ture the realistic physical degradation generated by the imaging system. To ad-dress the above limitations, this study introduces a heteroscedastic residual diffu-sion model (HDDPM) for low-count
brain PET recovery in which the forward corruption is itself intensity-aware. We designed a fixed, Poisson-based variance module to generate voxel-wise noise maps. These maps naturally place stronger noise perturbation on low-activity regions than high-activity ones, meanwhile the network predicts the low-to-standard-count residual under explicit dose-fraction conditioning. We evaluated our proposed model (HDDPM) alongside generative frameworks across three different scanners, using both internal and external da-tasets at various simulated dose levels (1% to 50%). HDDPM and isotropic DDPM showed comparable overall image quality, but HDDPM stood out in the lowest-dose (1%) external scans. It is highly reliable and significantly reduces measurement errors in both high- and low-activity regions, compared to the standard model. These results support that heteroscedastic noising with the pro-posed HDDPM is feasible, and it provides a physically motivated inductive bias for quantitative low-count PET recovery by reflecting the activity-dependent noise structure of PET.
Read the full abstract ▾