Model Checkpoints

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 36

Sep 30, 2026cs.LG

Reliability-Aware Checkpoint Selection for Domain Generalization

Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable probabilities on unseen target domains. Source-target distribution shifts can alter accuracy rankings, while accuracy alone does not measure predictive probability quality. We identify an empirical selection opportunity within fixed training trajectories: reselecting among checkpoints with near-optimal source accuracy can improve mean target probability quality with small observed changes in mean target accuracy. We study accuracy-constrained reliability selection (AC), which retains checkpoints within a tolerance of the best source-validation accuracy and ranks them by source reliability. Our reference rule aggregates within-set normalized negative log-likelihood (NLL) and class-wise calibration error (CwECE) using

D_\infty

. AC uses no target data and requires neither additional training nor weight averaging. We evaluate five domain generalization training algorithms on three benchmarks, using PACS to develop the objectives and a 0.5-percentage-point tolerance. In exploratory aggregation comparisons on 360 OfficeHome and TerraIncognita runs, the reference rule reduces mean target soft-bin squared-gap ECE and CwECE by 0.240% and 0.182%, respectively, and NLL by 0.030 relative to Source-Acc. Mean target accuracy changes by +0.213 percentage points. These results identify opportunities for reliability-aware reselection, while the additional benefit of joint over single-objective ranking remains unresolved.

Jinshi Liu, Jiahao Li, Pan Liu +5

Shenzhen University · Xiamen University · The Hong Kong University of Science and Technology (Guangzhou) +3

Multimodal Domain Generalization Model Checkpoints Validation

Sep 30, 2026cs.AI

Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs

Routing signals of modern vision transformers -- expert gates, attention-residual weights and halting scores -- often improve probes that predict whether the model is correct, and the improvement is commonly read as evidence that routing carries information about errors beyond the model's outputs. We test this inference directly: keeping real output-routing pairs, we redraw correctness labels from a frozen output-only generator fitted on disjoint data, so that routing is uninformative by construction. Under this exact label null, a width-matched MLP comparison still reports a routing gain in 51.3% of confidence-only evaluations (308/600), while a linear comparison reports none. Holding each training trajectory fixed on a six-model panel and selecting the checkpoint by validation log loss instead of validation accuracy removes the detections (50/120 to 0/120, and 83/120 to 0/120 in an independently implemented probe), identifying accuracy-based checkpoint selection as the cause; across all output views the raw detection rate falls from 27.5% (528/1,920) to zero observed detections. The repaired comparison is not sensitive, detecting an implanted signal of about 0.005 nats in 0/20 replicates in each of two matched settings, whereas a conditional permutation test built on an estimated routing law detects it in 11/20 and 10/20 and rejects rarely under the null. On real correctness labels, the conditional analysis yields model-relative evidence in five DeiT attention-residual families; in four it persists under two specified variants of the conditional law, and no family passes an additional noise criterion. Fitting a better probe and testing for incremental information are different problems, and each needs its own validation.

Wenhao Liang, Lin Yue, Wei Emma Zhang +3

Detection Performance Model Checkpoints Ground Truth Model Auditing Multilayer Perceptrons Uncertainty

Sep 29, 2026cs.CL

What Does Post-Training Change in Multilingual Reasoning?

Open-source reasoning models provide unequal access to reasoning capability across languages. When a model can solve a problem but cannot deliver a complete solution in the user's language, language becomes an access barrier rather than merely a source of performance variation. We audit Qwen3 checkpoints on competition-mathematics tasks in eleven languages. Across the ten non-English languages, only 15.4-17.9% of problems receive a correct, terminating solution with visible reasoning in the requested language in any of 16 samples, compared with 92.9% in English. To identify the source of this disparity, we evaluate thirteen endpoints from one model family, spanning released checkpoints, multilingual supervised fine-tuning (SFT) at two scales, controlled SFT ablations, and three reinforcement-learning (RL) reward formulations. We jointly track correctness, language adherence, termination, and delivery efficiency. The dominant bottleneck shifts across post-training stages. Released models often reason in English. Multilingual SFT restores target-language reasoning, but accuracy declines across multilingual, English-only, and single-language SFT runs, showing that this cost is not specific to multilingual mixing; non-English reasoning traces additionally become prone to non-terminating loops. RL restores termination in both arms at no cost in accuracy, but only the arm whose reward includes a language term delivers: rewarding correctness alone returns the model to English. Together, these stages establish a constructive post-training path from English-pivoted capability to multilingual reasoning that is reliably delivered.

Hongyang Li, Xiao Li, Caesar Wu +2

University of Luxembourg · Seafill Open-Source Community

Multilingual Language Models LLM Reasoning Strategies Post-Training Model Checkpoints Change

Sep 28, 2026cs.LG

QAM: Quadratic-Accurate Checkpoint Merging via Sequential Consistency

Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a different schedule. We study how accurately these checkpoints can reconstruct the endpoint of a sequential reference with prescribed update strengths. Under a common local transition model, two checkpoint-index moment conditions characterize all convex merges that agree with this reference through second order. We then prove an information limit that for nondegenerate profiles, no algorithm using only a fixed-length gradient-descent (GD) history with step size

h

can achieve

o(h^3)

endpoint error uniformly over a fixed class of smooth, strongly convex losses. The lower bound follows from two losses with identical GD checkpoint histories but sequential reference endpoints separated by

Ω(h^3)

. \textbf{Quadratic-Accurate Merging} (QAM) achieves a matching uniform

O(h^3)

endpoint error bound. Its explicit coefficients also define the unique profile-dependent merge that exactly matches the sequential GD reference across all fixed quadratic objectives. Across two public Adam checkpoint trajectories (SmolLM3-3B and OpenEuroLLM-Prelude-9B), three windows and three profiles per model, and 15 tasks, QAM shows mixed results for short windows and broader advantages over \textbf{Warmup-Stable and Merge} (WSM) for longer windows. Matched-moment GSM8K diagnostics further show that local consistency alone does not fully determine downstream scores. These results characterize the reconstruction limits of saved histories, provide a coefficient rule that attains the optimal rate, and assess its practical utility.

Shihao Wang, Rui Kong, Xinran Chen +7

University of Wisconsin – Madison · Baidu Inc. · University of Arizona +3

Model Checkpoints Continual Model Merging

Sep 28, 2026cs.AI

Query Expansion and Key Specialization in Transformer Attention Geometry

The projection of queries and keys are central to the attention mechanism in Transformer architectures. While they are mathematically symmetric, they play different roles in attention mechanisms. The question of whether there is an effect from their functional distinction on their geometric development in training remains unanswered. We investigate the problem through the training of small GPT-like Transformers on character-level WikiText-103 for three different depths (4, 6, and 8 layers), three types of initialization for queries and keys, and four random seeds, resulting in 36 runs and 54 trajectories of average layers across seeds. We track the effective dimensionality of those layers using participation ratios and discover that effective dimension of queries expand while keys shrink, and that

PR_Q - PR_K

is positive in all trajectories studied. In connection to attention, the shrinking of keys leads to a narrower spectrum of

QK^\top

and more peaked attention weights. In order to determine if this connection is causal or coincidental, we directly control the spectrum of keys during training across five seeds: restricting it to make it shrink sharpens the attention with high directional confidence, while keeping it constant to the level of initial dispersion makes attention softer. Additional token-level checkpoint analyses show that the monotonic paired-contrast trend is not universal across pretrained families, but survives as an early-training regime that later decays over a full pretraining run, and the link between interaction-rank geometry and attention entropy remains visible in several models.

Vidit Gupta, Siddhesh Nadkarni, Mihik Chaudhari +2

Dwarkadas J. Sanghvi College of Engineering Mumbai, India

Transformer Attention Transformer Architectures Intrinsic Dimensionality Model Checkpoints Monotonicity

Sep 12, 2026cs.AI

Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints

An unlearning audit reads its verdict off numbers that an unlearned model and its retrained reference each publish, and both also ship batch-normalization statistics that no gradient step wrote and no release records. Refitting them on kept data at bit-identical weights moves 47 of 221 released checkpoints past the spread their own release's seeds show, several inside a method whose average does not move: what moves is the checkpoint's property, not its method's. What does the moving is not the removed data surviving in the state: exchanging kept records for removed ones inside a fixed fitting pool moves a published cell by almost nothing, while how far a checkpoint's shipped state has drifted from any refit does track it. The consequence for a published decision is real but narrow: twelve verdicts cross, four clear a measured recalibration budget, two clear it on every replicate, and a population we trained and sited near its own criterion yields none. A release should therefore name the fitting convention beside the number, on the batch-normalized vision models where this channel exists.

Junlong Shen Xingyu Li

University of Alberta Edmonton, Canada

Model Checkpoints Unlearning Method Recalibration Post-Hoc Batch Normalization Model Auditing

Sep 9, 2026cs.CL

KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

Reusing key-value (KV) caches speeds up LLM inference by avoiding repeated computation on shared text. Standard prefix caching reuses a KV cache only when the LLM is the same and all preceding text is identical, but real workloads often break both conditions: RAG systems place different documents before the same one, agents with different system prompts read the same file or tool output, multi-agent workflows use specialized LLMs on shared material, and an updated model reads documents cached by its previous version. Because KV caches depend on both the preceding text and the model weights, direct reuse can reduce answer quality. Many methods repair or compress the reused cache, but each paper uses its own tasks, models, and cost measures, and existing benchmarks mainly test long-context processing or reuse of an unchanged prefix. We introduce KVShareArena, a benchmark and open evaluation framework for comparing them under the same conditions. KVShareArena has (1) reuse tests on 2,150 questions from three QA datasets, where the preceding text, the cache-writing LLM, or both change while the answering LLM and input stay fixed; (2) five dense and mixture-of-experts LLMs (4B-30B) and six LLM pairs where one version of an LLM reads caches written by another, for 33 model-dataset settings; (3) 11 repair and compression methods from six method classes; (4) four evaluation perspectives: answer quality, prefill computation, KV-cache memory, and latency; and (5) a common interface for adding new methods and an interactive leaderboard. Experiments yield two findings. First, both the quality loss from reuse and which repairs help depend on the LLM, even between two 8B models. Second, most repairs keep their quality when another LLM version wrote the cache, but a trained repair adapter loses quality in 12 of 18 pair-dataset tests. Code and data: https://github.com/xishi404/KVShare-Arena

Xi Shi, Mengxin Zheng, Qian Lou

University of Central Florida

Kv-Cache Management Large Language Model Serving Large Language Model Memory Question-Answering Benchmarks Model Checkpoints Shared Control

Sep 9, 2026cs.AI

Scored vs. Generated Readouts in Behavioral Language Models: An Empirical Study of Elicitation Format

Language models fine-tuned on customer behavior can predict outcomes and generate explanations, but these readouts are often treated as interchangeable. Holding model checkpoint and prompt content fixed, we compare probabilities obtained by scoring answer tokens with predictions generated after a written rationale. Across 13 model-domain cells covering four retail tasks in three markets, including two using fully public data and checkpoints, the scored readout ranks outcomes more accurately in 12 of 13 cells (two-sided sign test, p approximately 0.003), by 1.5 to 14.5 points in area under the receiver operating characteristic curve (AUC). Paired bootstrap confidence intervals exclude zero in every newly measured cell. The gap varies with task-specific supervision and mismatch between training and serving formats, ranging from -2.2 points for an untuned base model to +13.7 for rationale-format supervision. Analysis of approximately 9,000 rationales identifies two correlates: reduced reliance on the dominant predictive feature and convergence on stock formulations. Probability saturation does not track the gap. A third readout, eliciting a probability before any verdict, improves calibration (Brier score from 0.47 to 0.15) while ranking within noise of scoring, but only for outcome rates represented in training; it is worse than scoring when the scored head is already calibrated. We interpret these differences through the objectives matched by each readout, identify training choices that narrow the gap, and propose retaining generated rationales while sourcing ranking from the scored head.

Touchapon Kraisingkorn, Krittin Pachtrachai, Wachiravit Modecrua

Amity Research and Application Center (ARAC), Amity Group

Free-Form Textual Rationales Readout Elicitation Language Modeling Scores Empirical Study+3

Sep 8, 2026cs.AI

Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack

Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that the highest-scoring checkpoint will remain the best starting point for subsequent training. We show that this assumption can fail in a full 30B mixture-of-experts training pipeline. The checkpoints that perform better after the full downstream training stack also have higher solution density, i.e., retain downstream performance under local weight perturbations.

Sohir Maskey, Philipp Scholl, Jonas Knupp +2

Aleph Alpha

Model Checkpoints Intermediate Checkpoints Pretraining Downstream Fine-Tuning Downstream Reasoning

Sep 1, 2026cs.CL

Lagged Coupling: Internal Representations Become Readable Before They Become Causal

Across the full Pythia suite (160M-12B, eight checkpoints, four task families), a linear probe can read a target variable from the residual stream as early as step 1,000 at every scale -- yet steering along that same reading direction remains null-equivalent in 43 of 48 model-checkpoint cells. Internal readability systematically outruns causal efficacy, and the lag does not shrink with scale. We call this structure lagged coupling and decompose it into three dissociable tracks: (i) internal readability, saturated (AUROC >= 0.990) from the first checkpoint everywhere; (ii) behavioral readability, which develops gradually and progressively later at larger scales (12B reaches 0.909 only at the final checkpoint); (iii) causal efficacy, almost always null-equivalent, occasionally counterproductive early, with one isolated positive pulse (12B, step 8,000, z = +2.49) our grid cannot resolve. The ordering is dominantly read-before-write (11/11 units, no inversion). Representation headroom along the probe direction grows up to 57x with training and scale while causal write-in stays below 0.11% of headroom -- the variable is increasingly written into the representation and increasingly ignored by the readout. Under a fully pre-registered protocol, both single-onset hypotheses resolve INDETERMINATE (scale slope +0.24, 95% CI [-0.60, +0.87]; time vote 3:3) -- a disciplined negative explained by the three-track decomposition. A pre-registered OLMo-2 replication preserves the direction at attenuated magnitude. Our results caution against inferring steerability from probe accuracy and establish a developmental bottleneck: representation formation reliably outpaces causal readout consolidation.

Xining Xun

Tsingjiao Information Science (Beijing) Co., Ltd.

Readout Causal Developmental Trajectories Readability Model Checkpoints

Aug 30, 2026cs.AI

AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies

Latent world-action models avoid rendering future pixels by predicting an action-relevant visual subgoal in feature space. LaWAM established this formulation, but its original presentation left the world model, multimodal backbone, and deployment checkpoint tightly coupled. We introduce AcrossWAM1.0, a modularization and scaling study of this latent world-action stack. Rather than presenting latent subgoals as a new algorithm, we make the module boundary explicit: a policy adapter produces latent-action and action-generation contexts; a retained latent world decoder grounds the predicted transition in the current scene;and a flow-matching expert generates continuous action chunks. We further separate training-only teachers from the inference graph and provide a verifiable deployment export. On 2,000 paired LIBERO episodes, replacing a Qwen3-VL-2B backbone with Qwen3.5-0.8B yields 97.45% success versus 98.00% for the 2B model (a-0.55percentage-point difference; exact McNemarp=0.266). This does not prove equivalence, but it meets a prespecified two-point retention criterion. The compact, inference-reachable checkpoint contains 1,472.6M unique parameters, 42.4% fewer than the original 2B policy, while all retained tensors are bitwise identical to the source checkpoint. Cross-family execution is additionally checked with a MiniCPM-V adapter smoke test; closed-loop cross-family transfer remains an open evaluation. AcrossWAM1.0 therefore contributes an auditable software and evaluation boundary for compact latent world-action policies, distinct from LaWAM's original latent-subgoal contribution.

Yafei Zhang, Nan Wu

Across Physical AI, Beijing, China

Latent World Models Robot Policies High-Level Subgoal Generation Model Checkpoints Robot Systems

Aug 24, 2026eess.AS

The ISCSLP 2026 Real-World Audio-Visual Speech Enhancement Challenge

Audio-visual speech enhancement (AVSE) uses visual-speech cues from a target speaker to recover that speaker's speech from noisy or overlapping speech. Many widely used protocols construct mixed signals from separately recorded audio sources and assume reliable video, leaving their performance under natural overlap and visual failure insufficiently characterized. The Real-World AVSE Challenge evaluates two related settings. Track1 comprises two scenarios: real-world mixtures recorded with two speakers speaking simultaneously, without a corresponding clean reference signal, and synthetic remixes obtained by manually mixing the separately recorded speech of two speakers, with a clean reference signal available; Track2 reuses audio but pairs it with a degraded target video and contains additional 3-m far-field recordings. The speakers in the development and test sets are disjoint. Evaluation metrics include clean-waveform fidelity, learned quality estimates, transcription accuracy, and speaker identification. In the remix task on the development set, the baseline model achieved an SI-SDR of

-4.069

~~dB and an STOI of $0.388$ on Track~~1, and an SI-SDR of

-2.851

~~dB and an STOI of $0.470$ on Track~~2. We release the AV-ConvTasNet checkpoints, the offline evaluator, and the official baseline results on the development and test sets.

Kai Li, Wenze Ren, Junjie Li +11

1Tsinghua University · 2National Taiwan University · 3The Hong Kong Polytechnic University +8

Speech Enhancement Audio-Visual Consistency Speaker Waveforms Challenges Model Checkpoints

Aug 14, 2026cs.CL

Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification

Open-weight language models are fine-tuned, quantized, pruned, and merged, yet their provenance is often undocumented. We study data-free white-box lineage verification: can weights alone reveal whether two compatible model checkpoints share ancestry? Residual training produces a shared identity-aligned component in branch products, so this structure alone cannot establish ancestry. We remove it and compare checkpoint-specific structure across residual blocks, yielding a symmetric lineage score calibrated against independent checkpoints. On residual-MLP and GPT-2 benchmarks, the score separates fine-tuned, LoRA-merged, pruned, and quantized descendants from independent and distilled models (AUROC=1.0), distinguishing weight ancestry from behavioral similarity. Under function-preserving checkpoint laundering experiments, weight-space baselines lose margin or fail; our score remains unchanged and runs 76x faster than the nearest robust baseline on GPT-2. The projection-pairing signal appears across six language-model families and beyond, and a case study correctly identifies 3 related and 7 unrelated LLaMA-2 public checkpoints. Collectively, these results establish a passive, data-free provenance signal for compatible open-weight language-model checkpoints

Aman Singh Thakur, Rayan Khoury

Massachusetts Institute of Technology, USA

Model Checkpoints Model Weights Dataset Ownership Verification Distributional Signatures

Aug 9, 2026cs.CL

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the right trade-off changes with the workload. In the context of information retrieval (IR), a transformer-based model can be made smaller in three ways---using fewer layers, passing fewer tokens through the upper layers, or producing a shorter embedding---and each way saves a different compute resource. These options have been studied one at a time, each as its own method with its own code and training setup, which makes them hard to combine or adapt to a new model. We present~\ours to bring all three under one simple abstraction: a single object names any size the model can run at, and a short schedule lists the sizes to train. Training then produces one checkpoint that serves all of those sizes, and at deployment the user picks any of them. The same abstraction covers both retrievers and rerankers and both encoder and decoder models, as it works through interfaces that Hugging Face transformers already expose; a new backbone is a configuration change, not new modeling code. Prior methods---Matryoshka embeddings, early exit, 2D~~Matryoshka (e.g., Starbucks), and layerwise token compression---become special cases of our unified abstraction. The same interface also enables Matryoshka~~LTC (MLTC), which jointly trains several token-compression ratios in one retriever checkpoint. To validate our framework, we train 20 checkpoints across three backbones and two tasks: the quality curves are smooth, one checkpoint costs little over a model trained for a single size, and a controlled study confirms the wallclock speedups. We release the framework and all checkpoints as a resource for building elastic retrieval systems.

Yu Wang, Shengyao Zhuang, Xueguang Ma +4

University of Utah · 2The University of Queensland · University of Waterloo +1

Retrievers Transformer Architectures Token Compression Reranking Matryoshka Representation Learning Model Checkpoints

Aug 9, 2026cs.LG

Memory-Efficient Activation Checkpointing with Sliding Window and Hirschberg's Algorithm for 0/1 Knapsack Solving in PyTorch

Activation checkpointing minimizes the runtime of neural networks under a given memory budget, by selecting which intermediate tensors to store and which to recompute. PyTorch solves this as a 0/1 knapsack problem, where operations from a joint forward-backward computation graph are items with a memory cost (weight) and a runtime saving (value). The default solver, dp_knapsack, allocates a full dynamic programming (DP) table of shape

(n+1) \times (W+1)

, where

n

is the number of operations and

W

is the quantized memory budget. This method is resource-hungry and crashes at

n = 100

items on a machine with 64 GB RAM. In this paper, we introduce dp_knapsack_sliding_hirschberg, which combines the sliding window trick and Hirschberg's algorithm to reduce peak memory from

O(nW)

to

O(W)

while preserving the exact optimal solution. Our experiments show successful knapsack execution at

n = 2000

, where dp_knapsack fails at

n = 100

, a 20

\times

increase in computable problem size. In addition, our benchmarks show a consistent 25-28% runtime speedup over dp_knapsack. The implementation is merged into PyTorch and released in version 2.10.

Jędrzej Maczan

Cohere Labs Community Poland

Knapsack Constraint Pytorch Model Checkpoints Bounded-Memory Peak Memory Bidirectional Long Short-Term Memory+1

Aug 4, 2026cs.CV

When Oracle Conditioning Misleads Deployment: Conditioning-Availability Bias in Echocardiographic Segmentation

Conditional segmentation models may be trained and evaluated with auxiliary signals cleaner than those available at deployment. We study this protocol-level manifestation of shortcut learning and auxiliary-variable shift in phase-conditioned echocardiographic segmentation. The complementary gap pair measures loss on the deployable oracle-estimated pathway and probes sensitivity on the oracle-random pathway. On held-out CAMUS data, one strong-cyclic, oracle-selected run fails severely with estimated phase, while sensitivity to incorrect phase persists across three runs. On EchoNet-Dynamic, the current estimator remains usable, but random-phase testing reveals strong latent sensitivity. Deployment-aware checkpoint selection and phase perturbation reduce both gaps with little change in mean Dice. Exploratory subgroup analyses quantify variation across measured strata, and a downstream ejection fraction (EF) audit shows that recovering segmentation does not necessarily recover EF error or signed bias. Together, the gaps test whether oracle-conditioned performance survives the inference pathway actually available at deployment.

Dang P. M. Cao, Hieu D. Pham, Hieu Pham

College of Engineering and Computer Science, VinUniversity, Hanoi, Vietnam · VinUni-Illinois Smart Health Center, VinUniversity, Hanoi, Vietnam · Center for Innovations in Health Sciences, VinUniversity, Hanoi, Vietnam

Echocardiography Oracles Model Checkpoints Biases

Jul 30, 2026cs.CV

CXR-Retrieve: Compositional Text-to-Image Retrieval in Chest Radiography

Large chest radiography archives are difficult to search because most studies are paired only with free-text reports rather than structured clinical annotations. Vision-language models offer a natural interface for text-to-image retrieval, but current biomedical models are primarily optimized for report-to-image matching rather than for satisfying short clinical search queries. This creates an objective mismatch: a model may retrieve images related to words in the query while failing to satisfy the full clinical constraint, especially for conjunctions and negations such as ``atelectasis and no pneumonia.'' We introduce CXR-Retrieve, a structured benchmark for compositional chest X-ray text-to-image retrieval. The benchmark contains 5,159 test images from the official test-split of MIMIC-CXR-JPG and 145 textual queries spanning single and conjunction findings, both positive and negative. Relevance is defined by whether a retrieved image satisfies all asserted pathology constraints, rather than by whether it matches a paired report. We further propose a label-aware contrastive fine-tuning objective for clinical retrieval. Our method attracts image-text pairs with compatible asserted pathology constraints, including shared confirmed absences, while explicitly repelling contradictory pairs. Starting from the in-domain CXR-CLIP checkpoint, our method improves Precision@5 over CXR-CLIP by 8.5 percentage points on two-pathology conjunctions and by 22.0 percentage points on negation queries. These results show that reliable chest X-ray retrieval requires training objectives that model not only which findings are mentioned, but also how they are clinically asserted.

Tomer Erez, Moshe Kimhi, Chaim Baskin +1

Technion – Israel Institute of Technology · Ben-Gurion University of the Negev

Chest X-Ray Model Checkpoints

Jul 27, 2026cs.AI

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT

Developers judge a model checkpoint by how it behaves. After supervised fine-tuning (SFT), two checkpoints that perform about the same across relevant benchmarks are treated as interchangeable, equally ready for the next alignment stage, typically preference optimization. We ask whether this judgment misses a pretraining imprint: a difference that no post-SFT benchmark reveals, yet that decides how each checkpoint responds to further training. To find out, we run a controlled experiment on the final window of pretraining, the last data trained on before instruction tuning. Six branches fork from one partially pretrained checkpoint and differ only in this window: 500 million tokens, 0.1% to 1% of the tokens that precede it. Each branch trains its window on a single data source: generic web text, filtered web text, normative discourse, safety text, mathematical text, or synthetic educational text. SFT and post-training are then identical. After SFT the branches behave near-identically, within about one point on instruction following, refusal, and capability, yet the same post-training carries them to very different endpoints, under both a direct preference optimization update and a reinforcement learning update with a verifiable reward. We measure this deviation through refusal of harmful requests: when post-training begins the safety text branch refuses no more than the web text branch, yet by the end it has lost far less of its refusal. The other four branches gain little or no protection, so the effect is selective to what the window contained. The protection requires the safety text to arrive last rather than earlier in pretraining, and it reproduces on a second model family. What a model is pretrained on last shapes how it reacts to alignment. Therefore, a checkpoint should not be evaluated by its post-SFT behavior alone, and what it was trained on last should be reported with it.

Cen Lu, Yung-Chen Tang, Andrea Cavallaro

1EPFL · 2Idiap Research Institute

Model Checkpoints Post-Training Pretraining

Jul 2, 2026cs.CV

Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs

Modern pretrained vision models achieve strong accuracy but demand substantial GPU memory for fine-tuning, making edge deployment impractical. This paper compares five parameter-efficient fine-tuning (PEFT) methods (Full FT, LoRA, AdaLoRA, QLoRA, BitFit) on Transformers- (ViT-Small, TinyViT) and Mamba-based vision backbones (Vim-Small, MambaVision-T) under an on-device VRAM budget (e.g., 2 GB), together with three gradient-checkpointing strategies (none, static, and a proposed memory-budget-aware adaptive algorithm); and we evaluate three families of foundation-model baselines: zero-shot contrastive vision language models (OpenCLIP, SigLIP), self-supervised vision backbones with lightweight evaluation protocols (DINOv2), and autoregressive VLMs for prompt-based classification (PaliGemma, MobileVLM, SmolVLM). Experiments on CIFAR-100 and DTD report accuracy, training time, energy, and the NetScore family of multi-objective metrics, which we extend with two deployment-aware variants. QLoRA and BitFit cut energy 20-30% at a 1-2% accuracy cost; the adaptive algorithm reduces peak memory 43-79% with 9-30% energy overhead. DINOv2 surpasses fine-tuned models on CIFAR-100 (0.917 vs. 0.897) at a fraction of the energy, while small autoregressive VLMs remain uncompetitive.

Altay Toktassyn, Jurn-Gyu Park

Department of Computer Science, Nazarbayev University, Astana 010000, Kazakhstan

Parameter-Efficient Fine-Tuning Methods Vision Foundation Models Cpu-Gpu Hybrid Designs Vram Model Checkpoints Peak Memory+1

Jun 30, 2026cs.CV

Uncertainty-Aware Last-Layer Adaptation of RETFound for Referable Diabetic Retinopathy Screening Under Dataset Shift

This paper presents a safety-centered empirical evaluation of uncertainty-aware last-layer adaptation for referable diabetic retinopathy screening using RETFound, a self-supervised vision-transformer retinal foundation model used here as a frozen feature encoder, and the public APTOS 2019 and DDR diabetic retinopathy fundus image datasets. We compare a cached-feature softmax head, post-hoc temperature scaling, variational Bayesian last-layer heads, a diagonal Laplace last-layer approximation, and an SNGP-style cached-feature head. On APTOS, uncertainty-aware operating points improved sensitivity and selective-referral behavior. The strongest APTOS selective-referral result deferred approximately 20 percent of cases and reduced accepted-case false negatives to zero while preserving high accepted-case specificity. However, threshold tuning also reduced false negatives at high false-positive cost, so false-negative reduction alone was not unique to Bayesian modeling. On DDR, native Bayesian heads qualitatively reproduced the APTOS direction but with weaker tradeoffs, while the APTOS-trained SNGP checkpoint transferred poorly and failed to provide useful external selective-referral behavior. These results highlight the value of safety-centered evaluation beyond aggregate accuracy: uncertainty-aware last-layer heads can improve internal safety-oriented operating points, but trustworthy retinal screening claims require explicit safety-coverage evaluation and second-dataset validation under shift.

Karim Mardhani

University of Colorado Boulder Boulder, CO, USA

Glaucoma Detection Uncertainty-Aware Classification Model Checkpoints Safety Benchmarks Fetch Jobs

Jun 26, 2026cs.LG

Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis

Small Language Models (SLMs) are increasingly being considered for deployment on edge devices such as laptops, enabling private, low-latency, and locally personalized applications. However, personalization requires models to adapt over time to evolving user- or task-specific data, placing them in a continual learning setting. This creates the risk of catastrophic forgetting, where learning new information degrades performance on previously learned tasks or broader model capabilities. Recent benchmarks such as TRACE have shown that continual fine-tuning can significantly degrade the general abilities of aligned large language models. In this work, we present a study for sequential LoRA personalization of SLMs. We save model checkpoints after each adaptation stage and evaluate them on current tasks, previously seen tasks, and a fixed reference set. This checkpoint-level protocol enables us to monitor task performance, forgetting, and reference set drift over time. We show that lightweight reference set distributional diagnostics can reveal model-specific instability patterns during sequential LoRA personalization of SLMs, including cases where task-level metrics alone hide harmful adaptation. We hope this can highlight new research avenues for monitoring stability of SLMs in a continual learning setting.

Thomas S. Paula, Lucas S. Kupssinskü, Rodrigo C. Barros

MALTA, Machine Learning Theory and Applications Lab, PUCRS, Porto Alegre, Brazil · Kunumi Institute, Brazil

Small Large Language Models Replay-Based Continual Learning Continual Learning Model Checkpoints Personalization

Jun 19, 2026cs.CL

Test-Time Training with Next-Token Prediction

Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test time. We study whether this signal can define the inner-loop objective for test-time training (TTT) in pretrained long-context language models. Many TTT architectures require models to be trained with test-time adaptation in mind, limiting their direct applicability to released LLM checkpoints. While recent in-place TTT methods make fast-weight adaptation possible for pretrained LLMs without redesigning the backbone, they leave a central question unresolved: what should each test-time write store? Existing recipes train the fast weight to match a learned local value proxy but they are not directly tied to the self-supervised next-token prediction signal. We introduce Test-Time Training with Next-Token Prediction (TTT-NTP), a drop-in fast-weight adaptation method for pretrained LLMs that instead supervises updates using the model's own next contextual hidden state. This makes each local write follow the same causal computation that supports next-token prediction: the value target is a pointwise linear projection of a single next-position contextual state. On RULER Full-13, averaged over 4k to 32k contexts, TTT-NTP is the only method that consistently improves the released backbone across four models spanning three families and a 0.6-8B size range, by 3.9 points on Llama-3.1-8B, 3.0 on Mistral-7B-v0.3, 4.1 on Qwen3-4B, and 2.9 on Qwen3-0.6B. On the real-world LongBench-v2 long-document QA benchmark, TTT-NTP improves over the base model by 5.6 points on Llama-3.1-8B and 3.7 on Mistral-7B-v0.3, while preserving commonsense and knowledge performance. Our code is publicly available at https://github.com/yancyou/TTT-NTP.

Xuan Ouyang, Zefan Cai, Junjie Hu

University of Wisconsin–Madison

Test-Time Training Next-Token Prediction Autoregressive Token Prediction Test-Time Adaptation Model Checkpoints

Jun 11, 2026cs.LG

When Does Routing Become Interpretable? Causal Probes on Block Attention Residuals

Block Attention Residuals (Block AttnRes) by replace fixed additive residuals with a learned softmax over earlier depth-source representations, surfacing cross-layer routing as an inspectable tensor in the forward pass. This is a tempting interpretability target: information flow normally inferred indirectly is now directly observable. We ask whether such exposure suffices for mechanistic interpretation. We probe two same-scale (

0.6

B) Block AttnRes checkpoints under identical routing-ablation interventions: a vanilla Qwen3 inference-wrapped through a deterministic recency-bias schedule that the codebase admits as a routing-equivalent loading path, and a Block AttnRes Qwen3 trained from scratch with routing as part of optimisation. The wrapped baseline's routing weights are content-independent and reproduce the schedule's analytic prediction. The trained AttnRes checkpoint instead exhibits three localised routing motifs: an embedding-source pathway through early-layer MLP, a current-state pathway through early-layer attention and MLP, and an older-history pathway through late-layer attention. Beyond this stratification, we find a sharp dissociation between average routing mass and causal importance: in both sublayers, the largest mass slice is not the largest causal contribution, and one source family carries appreciable mass with no detectable causal role under intervention. Architectural exposure of routing is therefore necessary but not sufficient for mechanistic interpretation: structured depth routing emerges only when routing has been part of training, and even then, descriptive routing summaries should be treated as candidate hypotheses to be tested by causal interventions, not as evidence of mechanism in their own right.

Aydin Javadov

ETH Zurich

Model Checkpoints

Jun 8, 2026cs.LG

Quality Is Not a Safety Proxy Under Quantization

Quantized checkpoints are often screened first with quality metrics and only later, if at all, with direct safety tests. This paper audits that shortcut on a matched 51-row matrix spanning 6 models, 4 families, a 7-level GGUF ladder, and AWQ/GPTQ INT4 checkpoints. In this matrix the shortcut fails: all 36 quality-safety pairings split direction across models, and 9 hidden-danger rows plus 1 near-hidden-danger row show quality stable or improved while refusal falls by 12-68 percentage points. Seven of the 11 AWQ/GPTQ rows are hidden-danger. A four-probe mechanistic follow-up over the 17 Hugging Face-backed FP16/AWQ/GPTQ cells does not rescue it: entropy, refusal-direction, and calibration probes are weak or null separators of dangerous rows, and although probe-identified safety-associated neurons absorb 1.39

\times

more quantization error overall (

p < 5 \times 10^{-7}

), the effect is not regime-specific. Claude Sonnet 4 relabels 11,470 items in a predefined stratified set, agrees with the primary gemma3:12b judge on 89.9% of rows (

κ= 0.873

, 95% CI [0.866, 0.881]), and changes 0/10 hidden-danger cells. A calibrated study-internal behavioral screen -- the Refusal Template Stability Index (RTSI), built from four refusal-template drift features and calibrated on this matrix -- routes 10/10 hidden- or near-hidden-danger rows to direct safety testing (Wilson 95% CI lower bound 0.72) while leaving 23 of 45 non-baseline rows in a low-risk bucket under both in-sample scoring and row-level leave-one-out validation; on the same matrix, the best single-feature baselines (unique-prefix-rate-delta, raw refusal-rate delta) recover 9/10 and 8/10 respectively at matched bucket size, and cross-stack transfer requires recalibration. For the quantized checkpoints, model families, and safety outcomes studied here, retained quality cannot waive direct safety evaluation.

Sahil Kadadekar

Independent Researcher

Quantized Safety Benchmarks Model Checkpoints Refusals

Jun 8, 2026cs.LG

BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

As deep learning models scale, managing, inspecting, and modifying large checkpoints has become increasingly challenging. Researchers often need to alter model weights for layer restructuring, precision casting, low-rank factorization, and architectural debugging, yet these workflows often rely on fragile ad-hoc Python scripts. Here, we introduce BrainSurgery, a tool for robust and reproducible "tensor surgery" on neural network checkpoints, and provide a system demonstration covering four examples and three case studies from model upcycling to LoRA extraction. By abstracting storage formats and memory management, BrainSurgery executes complex transformations through declarative YAML plans. It supports structural modifications, mathematical transformations, and tensor reshaping through expressive regex and structural targeting, while built-in assertions validate tensor shapes, data types, and values to prevent silent errors. We envision that BrainSurgery will provide a strong foundation for future research through its reproducible and validated operations.

Gianluca Barmina, Annemette Broch Pirchert, Andrea Blasi Núñez +2

University of Southern Denmark

Model Checkpoints Model Weights Surgery Validation

May 27, 2026cs.LG

Model Merging by Output-Space Projection

Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups, TIES, and DARE - are computationally efficient and empirically successful, but rely on heuristic design choices and lack formal optimality guarantees. We show that merging can be formulated as a convex quadratic programme over residual updates, yielding weights that minimise a squared-output calibration objective using calibration inputs and fine-tuned model outputs, and subsuming existing methods as special cases. Our framework yields a closed-form diagnostic - the fraction of residual energy captured by a chosen basis - that predicts downstream merge quality using only the calibration set. Empirically, the QP matches or outperforms existing methods in the single-layer setting, and we characterise when the optimal basis provides significant gains over the cheaper diagonal QP. We extend to multi-layer merging via a sequential layer-wise algorithm and demonstrate consistent gains across language and vision benchmarks.

Bethan Evans, Benjamin Etheridge, Stephen Roberts +1

Department of Mathematics, University of Oxford, Oxford, UK · Department of Engineering Science, University of Oxford, Oxford, UK.

Continual Model Merging Multi--Task Learning Model Checkpoints Layer-Wise

May 27, 2026cs.SE

SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers

Smart contract decompilation aims to recover high-level source code from bytecode, but evaluating decompilers remains difficult because existing studies use narrow datasets, inconsistent metrics, and limited semantic consistency checks. This gap is increasingly important as large language models (LLMs) begin to generate source-like Solidity that may compile and appear plausible, even when its semantics diverge from the original contract. We introduce SCDBench, a dataset and benchmark methodology for LLM-based smart contract decompilation. The dataset contains 600 real-world Solidity contracts with paired bytecode inputs, ground-truth source code, and replayable semantic checkpoints. SCDBench evaluates decompiler outputs through four cumulative stages: format completeness, compilability, Application Binary Interface (ABI) recovery, and semantic consistency via differential replay. We evaluate Claude Opus 4.7, GPT-5.3-Codex, and GLM-5 in a zero-shot decompilation setting, including GLM-5 variants with and without extended reasoning and a zero-shot compilation-repair setting. The results show that frontier LLMs can often produce structured and compilable Solidity, but achieving semantic consistency remains far from solved: the best-performing frontier model perfectly decompiles only 42/600 contracts. We further show that introducing same-model compilation repair substantially improves performance at modest additional cost. SCDBench establishes a common ground for rigorous, reproducible evaluation and aims to accelerate the development of reliable smart contract decompilers for blockchain security and transparency.

Kaihua Qin, Dawn Song, Arthur Gervais

University of Warwick · UC Berkeley · University College London

Smart Contracts Disassembly Large Language Model Benchmarks Real-Tool Benchmarks High-Level Source Code Model Checkpoints

May 26, 2026cs.LG

How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks

Equivariant neural networks encode geometric symmetries by construction, yet they are often difficult to optimize and can underperform less constrained architectures. A growing body of work addresses this through architectural modifications such as constraint relaxation or approximate equivariance, while the role of the optimizer remains comparatively underexplored. We study this direction by comparing Muon and Adam across several equivariant and geometric architectures under pointcloud and molecular learning settings. On ModelNet40, where the comparison is clearest, Muon consistently improves over Adam across all architectures considered. We then analyze the trained ModelNet40 checkpoints through Hessian estimates, loss surface visualizations, and spectral properties of learned weights and intermediate representations. The checkpoints reached by Muon have larger Hessian curvature summaries but more regular loss surfaces, and their learned weights and representations have higher stable and effective ranks. These observations suggest that the interaction between optimizer design and geometric inductive bias deserves further attention from the community.

Teodor-Mihai Stupariu, Andrei Manolache

1Bitdefender, Romania · 2Tudor Vianu High School of Com · University of Stuttgart, Germany +1

Equivariant Neural Networks Muon Neural Network Inductive Bias Model Checkpoints

May 18, 2026cs.LG

Position: Weight Space Should Be a First-Class Generative AI Modality

Neural network checkpoints have quietly become a large-scale data resource: millions of trained weight vectors now exist, each encoding task-, domain-, and architecture-specific knowledge. This position paper argues that model checkpoints should be treated as a first-class data modality, and that generative modeling in weight space should be standardized as a core machine learning primitive. Recent advances demonstrate that neural weights can be synthesized on demand, often matching fine-tuning performance while reducing adaptation cost by orders of magnitude. We contend that these results reflect an underlying structural fact: high-performing models occupy low-dimensional, highly structured regions of weight space shaped by symmetry, flatness, modularity, and shared subspaces. Building on this view, we organize existing methods into a five-stage pipeline, survey applications where the approach is already practical, and clarify current limits: adapter-scale and conditional generation are advancing rapidly, while unrestricted frontier-scale checkpoint synthesis remains open. Our goal is to shift the community's default mindset from optimizing models per task to sampling models from learned weight distributions, accelerating toward an era in which AI systems routinely improve or create other AI systems.

Zhangyang Wang, Peihao Wang, Kai Wang

University of Texas at Austin · Tencent

Model Checkpoints Model Weights Weight-Space Generative Models Position

May 18, 2026cs.DC

TierCheck: Tiered Checkpointing for Fault Tolerance in Large Language Model Training

Large Language Model (LLM) training is frequently interrupted by a heterogeneous spectrum of failures, from common GPU crashes to catastrophic cluster-wide outages. Existing checkpointing systems rely on monolithic, single-tier storage backend, forcing a trade-off between state-saving overhead and recovery speed. We propose TierCheck, a cluster-aware tiered checkpointing system that aligns storage placement with failure heterogeneity. TierCheck adopts a three-tier design that maintains lightweight differential checkpoints in local and peer memory for fast localized recovery, while asynchronously migrating heavyweight base checkpoints to remote persistent storage. It also ensures strict global consistency across tiers without stalling training, and achieves fast cluster-aware checkpoint restoration during recovery. Evaluations on models up to 40 billion parameters show that TierCheck achieves low training overhead, reduces end-to-end checkpointing time to under 10s, and supports high-frequency checkpointing, ultimately striking an optimal balance between low-overhead persistence and fast recovery.

Shujie Han, Feng Jiang, Patrick P. C. Lee +5

Northwestern Polytechnical University · The Chinese University of Hong Kong · National University of Defense Technology

Model Checkpoints Large Language Model Training Fault Tolerance

May 17, 2026cs.AI

Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models

Recent work has fine-tuned language models on chess data and reported high benchmark scores as evidence that the resulting models can understand the rules of chess, play full chess games at a professional level, or generate human-readable explanations grounded in expert knowledge. We train KinGPT, a 25M-parameter character-level language model trained only on (position, best-move) pairs, who exceeds 3B-parameter ChessGPT on a 600-puzzle mate-in-N suite and 4B-parameter C1-4B over a 20-theme puzzle benchmark. We examine several claims made in existing literature regarding chess-trained language models and assert that their impressive benchmark performance is largely explained by pattern-matching. We also demonstrate how LLM-Modulo, a verifier-in-the-loop framework, raises RedPajama 3B's best move accuracy from 1.2% to 21.2% and move generation validity from 19.3% to 95.3% on mate-in-N chess puzzles, comparable to gains achieved from ChessGPT's fine-tuning on chess-specific web corpora at a fraction of the cost. Our results illustrate how pairing a general LLM with an external verifier offers a more flexible alternative to directly training on synthetic data for well-defined domains. We open source all training/evaluation code, datasets, puzzle samples, and KinGPT model checkpoints for reproducibility.

Ethan Tang

School of Computing and Augmented Intelligence · Arizona State University · Tempe, AZ 85281

Chess Model Checkpoints Memorization Fragility Synthetic Data

May 13, 2026cs.LG

Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking

Checkpoint selection for multimodal large language models (MLLMs) presents significant challenges when performance differentials are marginal and evaluation signals are prone to noise. Existing methodologies rely heavily on static benchmarks or pointwise scoring, which frequently misalign with in-the-wild usage and lack robust uncertainty estimation, particularly in OCR-heavy scenarios. In this work, we formulate checkpoint selection as a robust decision problem under evaluation uncertainty. We propose a multi-stage framework that integrates curated real-world data, structured LLM-based judgment, and multi-stage ranking protocols. The evaluation system orchestrates progressive refinement via pointwise filtering, listwise ranking, and pairwise comparison. To enhance reliability, we introduce subsampling-based confidence estimation and a percentile-based scoring formulation that captures distributional characteristics while penalizing tail failures. Furthermore, we demonstrate that data quality, specifically OCR readability, is a critical determinant of evaluation validity.

Qinwu Xu, Zhuoheng Li, Jessie Salas

Meta AI · Independent Researcher, previously Meta AI

Multimodal Evaluation Large Language Model Evaluation Model Checkpoints Multimodal Large Language Models Confidence Estimation Agentic Evaluations

Apr 30, 2026cs.OS

Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes

Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault tolerance, spot execution, RL rollout branching, and safe rollback-yet existing approaches fall into two extremes: application-level recovery preserves chat history but misses OS-side effects, while full per-turn checkpointing is correct but too expensive under dense co-location. The root cause is an agent-OS semantic gap: agent frameworks see tool calls but not their OS effects; the OS sees state changes but lacks turn-level context to judge recovery relevance. This gap hides massive sparsity: over 75% of agent turns produce no recovery-relevant state, so most checkpoints are unnecessary. Crab (Checkpoint-and-Restore for Agent SandBoxes) is a transparent host-side runtime that bridges this gap without modifying agents or C/R backends. An eBPF-based inspector classifies each turn's OS-visible effects to decide checkpoint granularity; a coordinator aligns checkpoints with turn boundaries and overlaps C/R with LLM wait time; and a host-scoped engine schedules checkpoint traffic across co-located sandboxes. On shell-intensive and code-repair workloads, Crab raises recovery correctness from 8% (chat-only) to 100%, cuts checkpoint traffic by up to 87%, and stays within 1.9% of fault-free execution time.

Tianyuan Wu, Chaokun Chang, Lunxi Cao +2

HKUST Hong Kong SAR, China

Sandbox Intermediate Checkpoints Model Checkpoints Semantic Gap

Feb 25, 2026cs.LG

Don't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stopping

Checkpoint selection is a standard component of neural network training, yet the validation criterion used to select a checkpoint is often chosen heuristically. Moreover, the same criterion may be used either only to rank checkpoints after completion of a predefined training run or also to determine when training should stop, thereby affecting both the selected checkpoint and the set of checkpoints available for selection. In this work, we systematically investigate the role of validation criteria under these two settings. We separately vary the training loss, the validation criterion, and the target evaluation metric, and compare post-hoc checkpoint selection, in which training proceeds for all predefined epochs, with patience-based early stopping, in which the validation criterion also controls training termination. We consider three Cross-Entropy, C-Loss, and PolyLoss as training losses, and accuracy, macro-F1, and Matthews correlation coefficient as target metrics. Selection quality is assessed through the relative gap between the test performance of the validation-selected checkpoint and the best-observed test performance for the same target metric over the complete predefined training run.

Andrea Apicella, Francesco Isgrò, Andrea Pollastro +1

Department of Information Engineering, Electrical Engineering, and Applied Mathematics (DIEM), University of Salerno, Via Giovanni Paolo II, 132, Fisciano (Salerno), 84084, Italy. · Department of Electrical Engineering and Information Technology, University of Naples Federico II, Via Claudio 21, Naples, 80125, Italy.

Early Stopping Model Checkpoints Evaluation Metrics Validation Performance Metric Early Layers

Sep 25, 2025cs.DC

Concertina: Data-Centric Adaptive Pipeline Parallelism for Efficient Heterogeneous Long-Context LLM Training

Long context training is crucial for extending LLM context windows. Existing schemes, such as sequence parallelism, incur substantial communication overhead. Pipeline parallelism (PP) reduces this cost, but its effectiveness hinges on partitioning granularity. Batch-level PP employing sequence packing exhibits high memory consumption in long-context scenarios, whereas token-level PP splitting sequences into slices alleviates memory overhead but may introduce performance degradation. Moreover, the skewed sequence-length distribution in real-world datasets defeats any monolithic, static choice of PP granularity. In this paper, we propose \textit{Dynamic Pipeline Parallelism} (DPP), which transforms PP granularity from a static design choice into a workload-adaptive optimization space over packed, split, and hybrid chunks. DPP further introduces a new coupling between heterogeneous pipeline scheduling and gradient checkpointing. To solve this coupling, \name co-optimizes dynamic chunk scheduling with \textit{Stage-Aware Chunk-Level Adaptive Checkpointing}. Comprehensive experiments demonstrate that \name achieves up to 1.69\texttimes\ speedup over FlexSP and up to 1.40\texttimes\ over MEPipe. The source code is available at https://github.com/wsjdsg/InfiniPipe-code.

Shiju Wang, Yujie Wang, Fangcheng Fu +6

Tsinghua University · Peking University · Shanghai Jiao Tong University +1

Efficient Long-Context Inference Large Language Model Training Model Checkpoints Instruction-Tuned Models Beethoven

Nov 22, 2024eess.IV

Cell as Point: One-Stage Framework for Efficient Cell Tracking

Conventional multi-stage cell tracking approaches rely heavily on detection or segmentation in each frame as a prerequisite, requiring substantial resources for high-quality segmentation masks and increasing the overall prediction time. To address these limitations, we propose CAP, a novel end-to-end one-stage framework that reimagines cell tracking by treating Cell as Point. Unlike traditional methods, CAP eliminates the need for explicit detection or segmentation, instead jointly tracking cells for sequences in one stage by leveraging the inherent correlations among their trajectories. This simplification reduces both labeling requirements and pipeline complexity. However, directly processing the entire sequence in one stage poses challenges related to data imbalance in capturing cell division events and long sequence inference. To solve these challenges, CAP introduces two key innovations: (1) adaptive event-guided (AEG) sampling, which prioritizes cell division events to mitigate the occurrence imbalance of cell events, and (2) the rolling-as-window (RAW) inference strategy, which ensures continuous and stable tracking of newly emerging cells over extended sequences. By removing the dependency on segmentation-based preprocessing while addressing the challenges of imbalanced occurrence of cell events and long-sequence tracking, CAP demonstrates promising cell tracking performance and is 8 to 32 times more efficient than existing methods. The code and model checkpoints are available at https://github.com/YXSong000/CAP.

Yaxuan Song, Jianan Fan, Heng Huang +2

School of Computer Science, The University of Sydney, Sydney, 2006, NSW, Australia · Department of Computer Science, University of Maryland College Park, College Park, 20742, Maryland, United States · Microsoft, Redmond, 98052, Washington, United States

Multi-Object Tracking Cells Feature Pyramid Model Checkpoints