Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

Release v5.24.0

Hugging Face Transformers v5.24.0 introduces several new models including Inkling 2 Mini, Apertus 1.5, WavTokenizer, Dory, HY4-VL, Omnilingual ASR, Lara Mini, SarvamMLA, SarvamMoE, and EXAONE. The release features a major breaking change renaming `past_key_values` and `cache_params` to `cache` across the library, standardizing cache handling. Multimodal models now return shared output classes instead of model-specific ones. Additional updates include improvements to generation, continuous batching, chat templates, pipelines, vision and audio processing, quantization, parallelization, exporters, and numerous bug fixes.

Introducing harness adapters: adapt your favorite model to your harness to improve performance and cost

Training Qwen3.8-27B with reinforcement learning inside custom agent harnesses (Pi, OpenCode, Hermes Agent) using LoRA adapters significantly improves performance and efficiency on targeted coding benchmarks. The adapted models achieve higher pass rates with fewer tool calls and tokens compared to the base model, even when evaluated under different harnesses. A merged 'super-adapter' maintains strong results across all three harnesses, demonstrating transferable capabilities. The full training pipeline—including task generation via Hub, validation with OpenEnv, and efficient AsyncGRPOTrainer—is made publicly available for reproducibility.

TALD: Transferability-Aware Logit Disentanglement for Cross-Modal Knowledge Distillation

arXiv:2611.25126v1 Announce Type: new Abstract: Cross-modal knowledge distillation can incur negative transfer when source-modality supervision conflicts with the target modality's discriminative characteristics. We propose TALD, a two-stage framework for Transferability-Aware Logit Disentanglement in class-aligned logit space. Guided by task-dependent self-benefiting and cross-modal exclusivity criteria, a Residual Disentangler decomposes logits from a teacher and an independently trained target-modality reference student into modality-general and modality-specific components. A Sample-Adaptive Modulator regulates decomposition constraints and sample-specific fusion weights. The learned modality-general components are then adaptively fused to supervise the final student. Across five benchmarks spanning vision, audio, and text, TALD achieves the largest mean accuracy gain and highest positive-transfer frequency among the compared methods. Across ten transfer directions with five runs each, TALD improves over training without distillation in 84% of evaluations, compared with at most 70% for the baselines, while offering a favorable accuracy-efficiency trade-off. We plan to release the code.

Thinflow: Organizing HPC Benchmarking Campaigns as Rerunnable Directory Trees

arXiv:2611.26526v1 Announce Type: new Abstract: A benchmarking campaign provides the measurements behind an HPC performance study: code variants are built, swept over core or node counts, and measured repeatedly. Moving such a campaign to another supercomputer or rerunning it months later requires work that is not part of the study itself. Job scripts are adapted to each supercomputer, and what exactly ran is often reconstructed afterwards. We present Thinflow, a small Bash engine for organizing HPC benchmarking campaigns as rerunnable directory trees of tasks and runs. A task is a directory with a short shell script next to the code. For each sweep, one command builds the code, runs the benchmarks, and plots the results. Thinflow derives the execution order from declared dependencies and writes it to a plain-text manifest. Per-supercomputer profiles submit the runs to a workload manager such as Slurm. Each run writes a provenance record of its environment, hardware, and parameters. The engine ships inside the campaign directory, so a campaign stays rerunnable without installing a separate tool and, once completed, may serve as a paper artifact. In a case study, we ran one campaign with identical task files on three Slurm partitions of two supercomputers, on up to 16 nodes. This strong-scaling study of matrix multiplication in C/OpenMP, C/MPI, and Julia/MPI comprises 37 task files with 217 non-comment lines. Its 455 benchmark runs recorded what differed per partition, chiefly profiles and command-line parameters. This suggests that such a campaign needs little structure beyond plain shell files.

Thoughts from Before and After AI

Article URL: https://chevyclutchfoot.substack.com/p/thought-process-before-and-after Comments URL: https://news.ycombinator.com/item?id=50572638 Points: 24 # Comments: 11

FACT: Fixed-Budget Allocation and Cross-Step Training for Speculative Decoding

arXiv:2611.23463v1 Announce Type: new Abstract: Speculative decoding accelerates language-model generation by verifying multiple draft tokens in a single target-model pass. However, better draft predictions and longer accepted continuations do not necessarily produce faster generation. To examine this gap, we present FACT (Fixed-Budget Allocation and Cross-Step Training), an experimental framework for studying how drafter training, candidate allocation, and execution conditions jointly affect acceptance and latency. Using a lightweight feature-prediction drafter with a frozen Llama-3-8B-Instruct target under greedy decoding, we first examine how training translates into accepted tokens. Backpropagating through predicted-feature rollouts with greater weight on early steps improves acceptance by 15-24% over uniformly weighted detached training, yet average rollout proxy cross-entropy does not reliably rank drafters by acceptance. Beyond prediction quality, the placement of draft candidates also matters: with a fixed 256-node budget and matched per-depth widths, replacing static allocation with confidence-guided allocation increases speedup over autoregressive decoding from $1.46\times$ to $2.02\times$ on HumanEval and from $1.31\times$ to $1.75\times$ on MT-Bench. This allocation benefit extends to an independently trained drafter, but stronger training does not consistently amplify it, showing that the two improvements do not necessarily reinforce each other. Even these speed gains depend on execution conditions: changing only host-thread settings can nearly eliminate speedup without changing acceptance. Together, these findings show why training and allocation must be evaluated jointly using both acceptance and end-to-end latency under controlled execution conditions.

FutureBench: A Renewable Framework for Evaluating Knowledge-Context Conflict in LLMs

arXiv:2611.23601v1 Announce Type: new Abstract: Asking a model to check retrieved text can also tell it which source to trust. We introduce FutureBench, a renewable framework for evaluating knowledge-context conflict using timestamped questions, controlled passage triplets, and no-context probes. Across 3,629 questions and six models, Verify (a prompt combining checking with passage priority) raises false-answer adoption in all five models tested on pre-cutoff events, mainly by displacing answers that were correct under Baseline, which allows both passage evidence and model knowledge. On post-cutoff events, only o4-mini increases adoption (+13.7 percentage points). A four-prompt comparison on 902 post-cutoff questions finds that passage priority without checking raises adoption, while moving to Verify lowers it in all five models. Adversarial-Aware, which warns of misleading passages and prioritizes model knowledge, restores 82.5-98.9% of displaced pre-cutoff answers with under one point of change in true-passage accuracy. FutureBench supports repeated evaluation on fixed cohorts and extension to new events as models change.

GRAFT: Execution-Guided Genetic Recombination for Agent Design

arXiv:2611.23509v1 Announce Type: new Abstract: Automated agent design searches for executable architectures that improve LLM-based agent performance, with evolutionary methods using language-model crossover to recombine promising mechanisms for task decomposition, model coordination, and verification. This search, however, is typically guided by aggregate fitness alone, which hides the instance-level successes and failures behind each score. We introduce Execution Guided Genetic Recombination for Agent Design (GRAFT), which uses aggregate fitness for selection and survival and parent-specific execution evidence to guide semantic crossover with integrated mutation. Its feedback harness reuses bounded samples of successful and failed runs from fitness evaluation, withholding reference answers and requiring no additional task executions. We evaluate GRAFT across six reasoning and programming settings using open-weight optimizer and executor models. It achieves a mean test accuracy of 82.0%, exceeding the strongest baseline by 9.8% points. Controlled ablations show that adding execution evidence improves test accuracy with initialization, search rules, repair policies, and evaluation budgets held fixed. Our results support the value of parent-specific execution evidence for evolutionary agent design.

GRAFT: Graph-Regularized Prototype Fields for Realistic Test-Time Adaptation of VLMs

arXiv:2611.23591v1 Announce Type: new Abstract: Unlabeled test data can improve the zero-shot classifier of a vision-language model, yet transductive and test-time adaptation methods often fall below the zero-shot baseline when only a few vocabulary classes are present in a batch or when streams are correlated. We trace this failure to a shared design: every class owns independent parameters estimated from its own samples, so absent or rare classes are left at biased text anchors or fitted to foreign samples. We propose Graph-Regularized Anchor-displacement Field Transduction (GRAFT), which models the adapted prototypes as text anchors plus a displacement field that is partially pooled over a semantic class graph through a Gaussian Markov random field prior, together with an explicit class-presence model. Inference is closed-form and gradient-free on cached features. Anchor-only shrinkage and a single global shift are the two extreme settings of the prior; absent classes are provably harmonic extensions of the present ones, and the pooling strength can be chosen by empirical Bayes. Under the realistic batch and online protocols on eleven benchmarks and four ImageNet shifts, GRAFT improves over the zero-shot model in every setting and over anchor-based transduction where few classes are present.

When Does Subspace Direction Matter for LoRA? Regime Analysis of the Magnitude Principle in Few-Shot Adaptation

arXiv:2611.23428v1 Announce Type: new Abstract: We show that the importance of a LoRA adapter's initial input-subspace direction is regime-dependent, and we characterize this dependence in theory and experiment. This refines the recent view that spectral initializers help through update magnitude alone. Direction matters most when labeled data are scarce relative to the representation dimension and the activation subspace used for initialization captures supervised task structure. In this regime, the adapter's row span remains sensitive to its starting point, making task-aligned initialization especially useful. A spiked-covariance perturbation analysis characterizes the finite-sample stability of the estimated subspace. A first-step analysis of LoRA training explains why the subspace's alignment with the task matters and motivates an alignment coefficient $\rho$ that closely tracks gains across classification tasks. We test this account with PivotLoRA, which initializes adapters from activation PCA at prediction-relevant positions and applies one output-preserving orthogonal pivot early in training. In few-shot BERT-base classification, PivotLoRA achieves the best average rank among 13 methods and improves over vanilla LoRA in 29 of 30 settings, even though it starts from a smaller input-factor initialization norm. Additional classification experiments extend the evaluation to 7B and 8B Llama decoders. Classification gains diminish with more labeled data, consistent with the proposed regime dependence. A targeted extension to completion-only reasoning also shows improvements on GSM8K and StrategyQA. These findings identify conditions under which initialization direction matters, with subspace-task alignment offering a low-cost diagnostic before training for classification.

Why your fine-tuning job takes longer than the FLOPs say

A study analyzing 272 production supervised fine-tuning jobs on NVIDIA H200 GPUs found that traditional FLOP-based estimates explain only 31% of actual training duration (R² = 0.31, MAE 12.41 h). In contrast, a CatBoost regressor using pre-dispatch job configuration features—including evaluation cadence, checkpoint policy, and per-GPU load—achieved R² = 0.98 with a mean absolute error of 1.71 h and median error of 0.51 h in cross-validation. The model outperforms analytical baselines by capturing overheads beyond compute, such as I/O contention and non-linear interactions between configuration variables. Results highlight the importance of training-specific signals and suggest that scheduling accuracy improves significantly when predictors account for operational overheads.

From Preference Data to Personalization: Tracing Sycophancy in Large Language Models

arXiv:2611.21650v1 Announce Type: new Abstract: Sycophancy in large language models is often measured as agreement with the user, yet agreement can be appropriate when the user's claim is valid, their preference is genuine, or their experience warrants acknowledgment. We study sycophancy as inappropriate agreement: validating a claim, preference, or self-assessment when the context calls for correction, qualification, or resistance. We introduce a validity-aware sycophancy grader and SycoDrift, a persona-targeted evaluation set of 3,298 validity-annotated probes with controlled annotations for user openness and stakes. We use this framework to analyze three sources of agreement pressure: human preference data, automated judge specification, and in-context personalization. First, preference for validating responses in human datasets (Chatbot Arena, HH-RLHF, Community Alignment) is weak and concentrated where agreement is often appropriate. Second, in a selected-value, single-model experiment, emphasized judge rubrics produce consistent but modest increases relative to paired suppressed rubrics, demonstrating a plausible mechanism for training-time amplification. Third, in off-policy evaluations across 14 models, inference-time personalization increases inappropriate agreement, with the largest effect from matched user profiles placed directly before the query.

Regularized Score Centering

arXiv:2611.21791v1 Announce Type: new Abstract: Asynchronous reinforcement learning increases training throughput, but data from stale policies and numerical mismatch between training and inference can destabilize learning. To stabilize off-policy learning, score centering (SC) removes the effect of reward baselines on the expected update. Our gradient diagnostics show less extreme gradients with SC than with importance sampling (IS), but SC can still fail when the learner moves far from the behavior policy that generated the data. To limit this policy mismatch, we introduce Regularized Score Centering (RSC), which adds a reverse Kullback-Leibler (KL) penalty to encourage the learner's next-token distribution to stay close to the behavior policy's next-token distribution. RSC works with or without truncated importance sampling (TIS), which caps token importance weights. Our theoretical analysis supports this approach, showing that KL regularization improves convergence guarantees. We evaluate dense and mixture-of-experts models on mathematical reasoning and agentic tasks, including online shopping, tool use, games, and fully asynchronous software engineering. RSC with TIS substantially improves sample efficiency across all agentic benchmarks, attaining higher training rewards with the same number of sampled responses. In final evaluations, it achieves top performance across all six agentic tasks, improving by 14.3% on AppWorld and reaching 9.9 times the strongest baseline's score on BabyAI.

Time-Series Models in the Streamhouse: A New Frontier and Use Cases

IBM's time-series foundation models, with over 50 million downloads, are now natively integrated into Confluent's platform, enabling real-time forecasting, anomaly detection, and optimization on streaming data using SQL. These models run on CPUs in both cloud and on-premises environments, supporting mission-critical applications across manufacturing, retail, banking, and airlines by delivering timely insights closer to decision-making points. The integration leverages Apache Flink and Confluent’s Streamhouse architecture to process data streams, apply AI-driven intelligence, and enable actions such as production optimization, fraud detection, supply chain planning, and trading execution—all in real time.

When Lower Harm Misleads: Auditing Concept Corrections

arXiv:2611.22084v1 Announce Type: new Abstract: An expert who corrects a concept prediction, such as a BI-RADS descriptor in breast ultrasound, expects the diagnosis to improve. Objectives that reduce the harm of such corrections are judged by harm and accuracy, yet harm also falls when a model responds less to every correction or starts from a worse uncorrected prediction, the reference for harm. We propose a correction audit, a reproducible evaluation protocol that separates these explanations: it splits each correction into harm and useful gain on identical events, separates the starting prediction from the correction response, and compares objectives with amplitude baselines matched in source harm. On three breast-ultrasound sources, worst-case correction training, evaluated from the mean-case model's start, lowers harm but gives up more useful gain in all 21 source comparisons pooled over six seeds, raising the corrected negative log-likelihood (NLL); from the same start, selecting between the objectives by harm picks the less helpful model on all three sources. On CUB, a monotonic harm penalty at its reported weight lowers path-level harm in all 80 concept sets while raising the NLL in all 80, almost entirely before any correction. At a fixed start, rescaling both responses to the same source harm reproduces the penalty's mean harm, useful gain and NLL on single-concept corrections within a prespecified margin of 0.0005 nat, although the two responses point in different directions. Lower harm therefore signals better corrections only when it is read together with useful gain, absolute risk and the start it is measured from.

Building trustworthy AI by fencing it in, not predicting it

In October this year, OpenAI disclosed that two of its AI agents had switched off the systems built to monitor them. One muted its own safety alerts after misreading an instruction not to send messages; the other removed its monitoring integration during migration, then said it hadn’t. No rule had told the agents to do…

VidEngram: Agentic Long-Term Video Understanding via Structured Hierarchical Memory

arXiv:2611.18578v1 Announce Type: new Abstract: Long-video question answering is wasteful and lossy when a multimodal model must re-encode the same video for every query: context limits force sparse sampling or truncation, and no reusable representation remains for later questions. We present VidEngram, an agentic video QA system that builds a persistent hierarchical memory once at ingest and answers later questions from that memory. VidEngram captions video and audio jointly with Qwen2.5-Omni, consolidates segment memories into episode and entity layers, and uses a text-only agentic planner with specialized retrieval tools to produce grounded answers. The web interface makes this process inspectable: users can watch memory formation, inspect retrieval traces, verify cited evidence in the video player, and explore entity relationships. On the full OmniVideoBench, VidEngram with a GPT-5-mini planner outperforms a strong single-pass Qwen2.5-Omni baseline (37.0% vs. 32.3%), with gains concentrated on longer videos where single-pass coverage becomes sparse. Because perception is paid once, subsequent queries use low-cost text-only planning.

Benchmarks Don't Talk Back: Learning Through Self-Disagreement

arXiv:2611.17563v1 Announce Type: new Abstract: A benchmark usually measures a language model alone with a question, and deployment rarely looks like that: answers get contested, and models give up correct ones under counter-reasoning that is itself wrong. We show that what fails there is not a shortfall of accuracy but a capability in its own right -- knowing when to hold a position and when to yield to a better one -- which we call dialectical competence. It stands on first-answer accuracy without following from it: a model can be made materially better at answering and no better at this, and training for accuracy alone can drift against it. Nor can it be bought at inference, by self-reflection or by sampling more. Taking a cue from the dialectical tradition in philosophy, in which productive opposition arises within a position rather than being imposed on it from outside, we hypothesize that this capability can be trained from opposition the model supplies itself. It states a position, generates the strongest case against that position -- its antithesis -- rules on whether the case stands, and is trained on that ruling, with no second model at training or at deployment. We call this learning through Self-Disagreement: reinforcement learning from verifiable rewards throughout, where the same check that scores an answer against its reference scores the ruling too, so no reward model, no preference data and no human annotation enter anywhere. The capability is trained rather than elicited: weak in the base model, it arrives with the reward, is not paid for out of first-answer accuracy, and holds against challengers the model never trained against, including ones stronger than itself. The opposition a model needs in order to improve, it turns out, need not come from outside it.

Small Open-Weight Language Models for Crowd Decision-Making: Capabilities and Limits of Output-Level Fusion and Linguistic Aggregation

arXiv:2611.17589v1 Announce Type: new Abstract: Small open-weight language models can run crowd decision-making (CDM) on an institution's own infrastructure, which keeps the checkpoint, the inference settings and the opinions under its control. Their judgements vary across repeated queries; whether repeating and aggregating them, often through the 2-tuple linguistic representation, settles the decision rather than the labels is untested. Five open-weight models of 8-36B total parameters on one consumer GPU and a hosted reference classify 474 TripAdvisor reviews of four London restaurants ten times each; three open-weight models repeat the protocol on 600 reviews of twelve Madrid restaurants. Continuous evaluations preserve resolution: snapping each review leaves 5 distinct values against 21-65, and snapping at every level at most two collective values. Sensitivity to the participants persists once run-to-run variability is reduced: in London, redrawing the reviewers keeps the winner on 47-81% of replicas against 86-100% for redrawing the runs. With simultaneous intervals over every pair of alternatives under crowd resampling, no system on either corpus names a single winner: in London every system keeps all four restaurants as candidates, and in Madrid the candidate sets hold five to eight of the twelve. Extra runs and output-level fusion stabilize the winner but do not remove that sensitivity, and the fusion does not beat its best member. The three larger open-weight models name the hosted reference's London winner and at least match its per-review correlation with the reviewers' stars, so small open-weight models can support local CDM, reported as candidate sets with margins rather than forced rankings.