LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2608.21022v1 Announce Type: new Abstract: Micro-actions are subtle, short, low-amplitude body movements, such as a fidgeting hand or a slight head tilt, that humans perform with little consciou...
MatMMExtract is an open‑source pipeline that disassembles compound scientific figures into individual sub‑panels and generates structured, grounded image‑text pairs using a large language model guided by a materials science taxonomy. Applied to 14,810 open‑access articles, it produced 391,606 panel‑level pairs with sub‑captions, a two‑level visualisation category (19 classes, 100+ subtypes), and scientific summaries. The project also introduces MaterialScope, a 2,811‑figure detection dataset, and demonstrates that Gemini 3.1 Flash Lite yields high‑quality annotations with low hallucination, while a dual‑encoder baseline outperforms zero‑shot CLIP on the resulting MatSciFig dataset.
The paper introduces a synthetic Bengali speech dataset tailored for telecom customer‑care applications, comprising 10,000 audio‑text pairs (≈26.82 hours) with predefined train, validation, and test splits. The data were generated using OmniVoice voice‑cloning, and include both original and normalized transcripts for ASR/STT use. Automatic intelligibility evaluation with a fine‑tuned Whisper model shows an average WER of 2.54% and CER of 0.59%, indicating strong text‑audio consistency, while the authors note limitations of synthetic speech and STT‑based evaluation.
arXiv:2608.21204v1 Announce Type: cross Abstract: Behaviour Cloning (BC) has driven remarkable progress in robot manipulation, yet it is fundamentally limited by its inability to self-improve: a poli...
The paper introduces Conformalized Agentic Search (CAS), a framework that applies Conformal Prediction to improve the reliability of search agents during reinforcement learning fine-tuning. CAS uses an Adaptive Prediction Set (APS) to dynamically truncate retrieved documents based on statistical coverage, and Adaptive Conformal Inference (ACI) to construct confidence-aware prediction sets that penalize low‑confidence trajectories in the Group Relative Policy Optimization objective. Experiments on single‑hop and multi‑hop QA datasets show that CAS enhances reasoning accuracy and reduces redundant tool invocations, offering a more reliable and efficient agent paradigm.
arXiv:2608.20394v1 Announce Type: cross Abstract: Industry pipelines that turn speech into supervised fine-tuning (SFT) data via multi-stage refinement are increasingly adopted but, to our knowledge,...
ZenGen is a comprehensive framework designed to develop socially intelligent large language models (LLMs). It introduces SoMBench, a psychology‑grounded benchmark with 3 primary and 17 secondary dimensions, and shows that current LLMs perform poorly on social cognition tasks. ZenGen combines supervised fine‑tuning, on‑policy distillation, and rubric‑based reinforcement learning to improve internalization, while Actio provides deployment‑time grounding with typed supports such as PRISM, Starling, SAGE, and gated RAG, yielding significant performance gains across benchmarks.
Instruction-Based Video Editing by Repurposing an Image Editing Model demonstrates that a strong image‑editing model can be adapted to edit videos by operating on video‑VAE latents. The authors tile latent frames into a large virtual image, reuse the editor’s positional encoding, and bridge latent spaces with lightweight projections, fine‑tuning on Ditto‑1M editing triplets. Their experiments show that per‑frame video latents are close enough to the image domain that mature image‑editing priors transfer with minimal adaptation.
arXiv:2608.20814v1 Announce Type: new Abstract: Though Multimodal Large Language Models (MLLMs) have shown impressive potential in video understanding, long video understanding (LVU) remains challeng...
arXiv:2606.15765v2 Announce Type: replace Abstract: Vision foundation models (VFMs) exhibit complementary strengths shaped by their pretraining objectives. Yet prevailing methods for multi-task dense...
arXiv:2606.13971v3 Announce Type: replace Abstract: While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current pr...
The study investigates whether open‑weight language models can introspect on their own internal computations. Using the Open‑Weight Masked Introspection (OWMI) framework, researchers intervened on various internal components of eight models and asked them to report whether changes had occurred. Across 78,000 measurements, none of the models reliably distinguished real interventions from sham ones, with AUROC values essentially at chance. Why It Matters: The findings suggest that current open‑weight models lack the ability to audit their own internal states, highlighting a limitation for oversight that relies on a model’s self‑reporting.
The study presents a reinforcement learning approach, Advantage Aggregation (AdvA), to control the X‑point target (XPT) divertor in the EXL‑50U tokamak experiment. By preserving objective‑wise temporal credit and applying a residual correction, AdvA‑PPO outperforms standard Reward‑PPO and a feedforward‑plus‑PID baseline, achieving a 0.81 worst‑channel score and reducing X‑point flux RMSE by roughly 20× over a 500 ms rollout. The method remains robust under measurement uncertainties and across varied initial equilibria, offering a simulation‑based foundation for future real‑time XPT validation on EXL‑50U.
Re$^3$Cap introduces a retrieval‑guided refinement strategy for image captioning that leverages multi‑modal retrieval as a reasoning signal. The method, built on a Caption Refinement Suggester and a Caption Quality Assessor, detects hallucinations and omissions to produce more accurate and detailed captions without extra annotations. Experiments show it surpasses supervised fine‑tuning and improves relation reasoning by 8.64% on the COCO‑LN500 benchmark.
arXiv:2505.18930v2 Announce Type: replace-cross Abstract: Early weed identification is crucial for effective management and control, and researchers, agronomists, and technology developers are increa...
The paper identifies a specific issue in supervised fine‑tuning (SFT) of large language models called factual access failure, where models can recognize correct facts under constrained tests but fail to generate them in open‑ended settings. It demonstrates that SFT can cause both genuine wrong answers and expression‑level errors such as verbosity or formatting mismatches. To mitigate this, the authors propose Recall‑Anchored Distillation (RAD), a self‑distillation method that aligns the fine‑tuned model with the base model’s soft output distribution on unlabeled out‑of‑distribution text, thereby recovering lost factual recall without needing labeled data.
arXiv:2608.21024v1 Announce Type: new Abstract: Modern neural network training increasingly uses matrix-aware optimizers, yet their conditioned matrix step is typically added directly to the weight,...
The paper investigates how agentic systems decide between acting and abstaining, focusing on the fidelity of their reasoning explanations. Using Qwen3‑8B in a multi‑party conversation setting, the authors compare direct decision policies, reasoning policies, supervised fine‑tuning, and reinforcement learning, finding a trade‑off: strong direct policies yield higher performance but no traceable reasoning, while reasoning policies provide an audit trail at the cost of lower recall. The study also uncovers that exposing reasoning can alter the agent’s policy and that common faithfulness metrics may overstate the alignment between reasoning and decisions.
TLive-Omni is an omni‑modal understanding model designed for e‑commerce live streaming, integrating image, video, audio, and text inputs into a unified representation. It introduces Per‑vGrid for timestamped token organization, a three‑stage supervised training pipeline, and a Faithful‑RFT reinforcement fine‑tuning stage to enhance answer faithfulness and expression quality. The model is supported by a scenario‑oriented capability taxonomy and a compact data production engine that generates training signals for tasks such as speech recognition, product visual grounding, and omni‑modal QA, achieving strong performance on live‑commerce benchmarks and good generalization to general tasks.
The paper demonstrates that a prompt’s influence is not inherent to the prompt itself but depends on the model, as prompts optimized for one model degrade on another and rankings shift under neutral reformatting. By examining a task‑free structural readout—specifically the fixed‑point behavior of a short‑window argmax map—the authors show that nine tokens of conditioning can move the fixed‑point fraction across most of its range, altering structural classes and model rankings, while instruction tuning has no effect. Attempts to explain this phenomenon through prefix length, content type, bidirectionality, or attention‑sink dominance all fail, indicating that the prompt‑model pair is the fundamental unit of explanation. whyItMatters":"The study reveals that prompt effectiveness is model‑specific and that simple structural readouts can capture this interaction, challenging assumptions about prompt generality and guiding future prompt‑engineering efforts."