{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/instruction-following/papers/8","list_of":"/task/instruction-following","task":"Instruction Following","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":8,"pages_in_order":12,"rows_per_page":100,"rows":[701,800],"of":1135,"counts":{"archive_papers_tagged":1135,"with_a_code_link":609,"where_syntology_ran_a_sample":311,"not_listed_spam_title":0,"listed":1135,"listed_where_code_ran":311,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":255,"every_run_a_failure_of_syntologys_instrument":56,"listed_with_a_run_with_no_instrument_failure":255,"listed_every_run_a_failure_of_syntologys_instrument":56,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/instruction-following","prev":"/task/instruction-following/papers/7","next":"/task/instruction-following/papers/9","papers":[{"url":null,"slug":"separator-injection-attack-uncovering","title":"Separator Injection Attack: Uncovering Dialogue Biases in Large Language Models Caused by Role Separators","date":"2025-04-08","arxiv_id":"2504.05689","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-hidden-space-of-safety-understanding","title":"The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context","date":"2025-04-03","arxiv_id":"2504.02708","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectively-controlling-reasoning-models","title":"Effectively Controlling Reasoning Models through Thinking Intervention","date":"2025-03-31","arxiv_id":"2503.24370","repositories_listed":0,"syntology":null},{"url":null,"slug":"pay-more-attention-to-the-robustness-of","title":"Pay More Attention to the Robustness of Prompt for Instruction Data Mining","date":"2025-03-31","arxiv_id":"2503.24028","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-instruct-for-visual-instruction","title":"Learning to Instruct for Visual Instruction Tuning","date":"2025-03-28","arxiv_id":"2503.22215","repositories_listed":0,"syntology":null},{"url":null,"slug":"gemma-3-technical-report","title":"Gemma 3 Technical Report","date":"2025-03-25","arxiv_id":"2503.19786","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnigeo-towards-a-multimodal-large-language","title":"OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence","date":"2025-03-20","arxiv_id":"2503.16326","repositories_listed":0,"syntology":null},{"url":null,"slug":"thinkpatterns-21k-a-systematic-study-on-the","title":"ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs","date":"2025-03-17","arxiv_id":"2503.12918","repositories_listed":0,"syntology":null},{"url":null,"slug":"icco-learning-an-instruction-conditioned","title":"ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control","date":"2025-03-15","arxiv_id":"2503.12122","repositories_listed":0,"syntology":null},{"url":null,"slug":"d3-diversity-difficulty-and-dependability","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","date":"2025-03-14","arxiv_id":"2503.11441","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-subspace-representation-fine","title":"Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models","date":"2025-03-13","arxiv_id":"2503.10617","repositories_listed":0,"syntology":null},{"url":null,"slug":"exo2ego-exocentric-knowledge-guided-mllm-for","title":"Exo2Ego: Exocentric Knowledge Guided MLLM for Egocentric Video Understanding","date":"2025-03-12","arxiv_id":"2503.09143","repositories_listed":0,"syntology":null},{"url":null,"slug":"got-compute-but-no-data-lessons-from-post","title":"Got Compute, but No Data: Lessons From Post-training a Finnish LLM","date":"2025-03-12","arxiv_id":"2503.09407","repositories_listed":0,"syntology":null},{"url":null,"slug":"dafe-llm-based-evaluation-through-dynamic","title":"DAFE: LLM-Based Evaluation Through Dynamic Arbitration for Free-Form Question-Answering","date":"2025-03-11","arxiv_id":"2503.08542","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-world-skill-discovery-from-unsegmented","title":"Open-World Skill Discovery from Unsegmented Demonstrations","date":"2025-03-11","arxiv_id":"2503.10684","repositories_listed":0,"syntology":null},{"url":"/paper/xifbench-evaluating-large-language-models-on","slug":"xifbench-evaluating-large-language-models-on","title":"XIFBench: Evaluating Large Language Models on Multilingual Instruction Following","date":"2025-03-10","arxiv_id":"2503.07539","repositories_listed":0,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xifbench-evaluating-large-language-models-on#ran","syntology_url":"https://syntology.ai/paper/2503.07539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07539"}},"official":null}},{"url":null,"slug":"dr-genre-reinforcement-learning-from","title":"Dr Genre: Reinforcement Learning from Decoupled LLM Feedback for Generic Text Rewriting","date":"2025-03-09","arxiv_id":"2503.06781","repositories_listed":0,"syntology":null},{"url":null,"slug":"s2s-arena-evaluating-speech2speech-protocols","title":"S2S-Arena, Evaluating Speech2Speech Protocols on Instruction Following with Paralinguistic Information","date":"2025-03-07","arxiv_id":"2503.05085","repositories_listed":0,"syntology":null},{"url":null,"slug":"ifir-a-comprehensive-benchmark-for-evaluating","title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","date":"2025-03-06","arxiv_id":"2503.04644","repositories_listed":0,"syntology":null},{"url":null,"slug":"codeif-bench-evaluating-instruction-following","title":"CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation","date":"2025-03-05","arxiv_id":"2503.22688","repositories_listed":0,"syntology":null},{"url":null,"slug":"lewis-layer-wise-sparsity-a-training-free","title":"LEWIS (LayEr WIse Sparsity) -- A Training Free Guided Model Merging Approach","date":"2025-03-05","arxiv_id":"2503.03874","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-learning-of-diverse-code-edits","title":"Robust Learning of Diverse Code Edits","date":"2025-03-05","arxiv_id":"2503.03656","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-mind-model-reimagining-autonomous","title":"Unified Mind Model: Reimagining Autonomous Agents in the LLM Era","date":"2025-03-05","arxiv_id":"2503.03459","repositories_listed":0,"syntology":null},{"url":null,"slug":"inserter-speech-instruction-following-with","title":"InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training","date":"2025-03-04","arxiv_id":"2503.02769","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-value-function-optimization-for","title":"Iterative Value Function Optimization for Guided Decoding","date":"2025-03-04","arxiv_id":"2503.02368","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-vs-instruction-tuning-the","title":"In-context Learning vs. Instruction Tuning: The Case of Small and Multilingual Language Models","date":"2025-03-03","arxiv_id":"2503.01611","repositories_listed":0,"syntology":null},{"url":null,"slug":"triple-phase-transitions-understanding-the","title":"Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective","date":"2025-02-28","arxiv_id":"2502.20779","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-aware-task-arithmetic-disentangling","title":"Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge","date":"2025-02-27","arxiv_id":"2502.20186","repositories_listed":0,"syntology":null},{"url":null,"slug":"dataman-data-manager-for-pre-training-large","title":"DataMan: Data Manager for Pre-training Large Language Models","date":"2025-02-26","arxiv_id":"2502.19363","repositories_listed":0,"syntology":null},{"url":null,"slug":"ground-level-viewpoint-vision-and-language","title":"Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments","date":"2025-02-26","arxiv_id":"2502.19024","repositories_listed":0,"syntology":null},{"url":null,"slug":"hi-robot-open-ended-instruction-following","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","date":"2025-02-26","arxiv_id":"2502.19417","repositories_listed":0,"syntology":null},{"url":null,"slug":"uro-bench-a-comprehensive-benchmark-for-end","title":"URO-Bench: A Comprehensive Benchmark for End-to-End Spoken Dialogue Models","date":"2025-02-25","arxiv_id":"2502.17810","repositories_listed":0,"syntology":null},{"url":null,"slug":"ateb-evaluating-and-improving-advanced-nlp","title":"ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding Models","date":"2025-02-24","arxiv_id":"2502.16766","repositories_listed":0,"syntology":null},{"url":null,"slug":"urdullama-1-0-dataset-curation-preprocessing","title":"UrduLLaMA 1.0: Dataset Curation, Preprocessing, and Evaluation in Low-Resource Settings","date":"2025-02-24","arxiv_id":"2502.16961","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-level-large-language-model-training","title":"Sequence-level Large Language Model Training with Contrastive Preference Optimization","date":"2025-02-23","arxiv_id":"2502.16433","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-tuning-on-public-government-and","title":"Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakh","date":"2025-02-19","arxiv_id":"2502.13647","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-non-transitivity-in-llm-as-a","title":"Investigating Non-Transitivity in LLM-as-a-Judge","date":"2025-02-19","arxiv_id":"2502.14074","repositories_listed":0,"syntology":null},{"url":null,"slug":"opensearch-sql-enhancing-text-to-sql-with","title":"OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment","date":"2025-02-19","arxiv_id":"2502.14913","repositories_listed":0,"syntology":null},{"url":null,"slug":"talkplay-multimodal-music-recommendation-with","title":"TALKPLAY: Multimodal Music Recommendation with Large Language Models","date":"2025-02-19","arxiv_id":"2502.13713","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-arithmetic-learning-improves","title":"Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models","date":"2025-02-18","arxiv_id":"2502.12855","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-we-really-need-visual-instructions-towards","title":"Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models","date":"2025-02-17","arxiv_id":"2502.11427","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-keep-a-promise-scaling-language","title":"Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding","date":"2025-02-17","arxiv_id":"2502.11517","repositories_listed":0,"syntology":null},{"url":null,"slug":"saif-a-sparse-autoencoder-framework-for","title":"SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models","date":"2025-02-17","arxiv_id":"2502.11356","repositories_listed":0,"syntology":null},{"url":null,"slug":"e2lvlm-evidence-enhanced-large-vision","title":"E2LVLM:Evidence-Enhanced Large Vision-Language Model for Multimodal Out-of-Context Misinformation Detection","date":"2025-02-12","arxiv_id":"2502.10455","repositories_listed":0,"syntology":null},{"url":null,"slug":"2502-06659","title":"Who Taught You That? Tracing Teachers in Model Distillation","date":"2025-02-10","arxiv_id":"2502.06659","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-representation-alignment-successor","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","date":"2025-02-08","arxiv_id":"2502.05454","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypencoder-hypernetworks-for-information","title":"Hypencoder: Hypernetworks for Information Retrieval","date":"2025-02-07","arxiv_id":"2502.05364","repositories_listed":0,"syntology":null},{"url":null,"slug":"verifiable-format-control-for-large-language","title":"Verifiable Format Control for Large Language Model Generations","date":"2025-02-06","arxiv_id":"2502.04498","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-can-be-easily-confused-by-instructional","title":"LLMs can be easily Confused by Instructional Distractions","date":"2025-02-05","arxiv_id":"2502.04362","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-an-llm-as-a-judge-model-pipeline","title":"Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons","date":"2025-02-05","arxiv_id":"2502.02988","repositories_listed":0,"syntology":null},{"url":null,"slug":"smollm2-when-smol-goes-big-data-centric","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","date":"2025-02-04","arxiv_id":"2502.02737","repositories_listed":0,"syntology":null},{"url":null,"slug":"vaibot-shuttle-between-the-instructions-and","title":"Shuttle Between the Instructions and the Parameters of Large Language Models","date":"2025-02-04","arxiv_id":"2502.02315","repositories_listed":0,"syntology":null},{"url":null,"slug":"bare-combining-base-and-instruction-tuned","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","date":"2025-02-03","arxiv_id":"2502.01697","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-human-perception-dynamics-for","title":"Learning Human Perception Dynamics for Informative Robot Communication","date":"2025-02-03","arxiv_id":"2502.01857","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-length-bias-in-preference","title":"Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling","date":"2025-02-02","arxiv_id":"2502.00814","repositories_listed":0,"syntology":null},{"url":null,"slug":"reforce-a-text-to-sql-agent-with-self","title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Format Restriction, and Column Exploration","date":"2025-02-02","arxiv_id":"2502.00675","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-bottlenecks-in-safety-fine-tuning","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","date":"2025-01-30","arxiv_id":"2501.18533","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-quantized-representation-for","title":"Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models","date":"2025-01-30","arxiv_id":"2501.18119","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-moe-a-mixture-of-experts-multi-modal-llm","title":"3D-MoE: A Mixture-of-Experts Multi-modal LLM for 3D Vision and Pose Diffusion via Rectified Flow","date":"2025-01-28","arxiv_id":"2501.16698","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-well-can-llms-grade-essays-in-arabic","title":"How well can LLMs Grade Essays in Arabic?","date":"2025-01-27","arxiv_id":"2501.16516","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-math-reasoning-in-language-models","title":"Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages","date":"2025-01-23","arxiv_id":"2501.14002","repositories_listed":0,"syntology":null},{"url":null,"slug":"compositional-instruction-following-with","title":"Compositional Instruction Following with Language Models and Reinforcement Learning","date":"2025-01-21","arxiv_id":"2501.12539","repositories_listed":0,"syntology":null},{"url":null,"slug":"bap-v2-an-enhanced-task-framework-for","title":"BAP v2: An Enhanced Task Framework for Instruction Following in Minecraft Dialogues","date":"2025-01-18","arxiv_id":"2501.10836","repositories_listed":0,"syntology":null},{"url":null,"slug":"dna-1-0-technical-report","title":"DNA 1.0 Technical Report","date":"2025-01-18","arxiv_id":"2501.10648","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-and-few-shot-learning-with","title":"Zero-shot and Few-shot Learning with Instruction-following LLMs for Claim Matching in Automated Fact-checking","date":"2025-01-18","arxiv_id":"2501.10860","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-cot-exploring-chain-of-thought","title":"Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model","date":"2025-01-13","arxiv_id":"2501.07246","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-evaluation-of-large-language-5","title":"A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Context","date":"2025-01-12","arxiv_id":"2501.06859","repositories_listed":0,"syntology":null},{"url":null,"slug":"migician-revealing-the-magic-of-free-form","title":"Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models","date":"2025-01-10","arxiv_id":"2501.05767","repositories_listed":0,"syntology":null},{"url":null,"slug":"minmo-a-multimodal-large-language-model-for","title":"MinMo: A Multimodal Large Language Model for Seamless Voice Interaction","date":"2025-01-10","arxiv_id":"2501.06282","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-vision-language-model-training-via","title":"Scalable Vision Language Model Training via High Quality Data Curation","date":"2025-01-10","arxiv_id":"2501.05952","repositories_listed":0,"syntology":null},{"url":null,"slug":"longvitu-instruction-tuning-for-long-form","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","date":"2025-01-09","arxiv_id":"2501.05037","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-and-planning-in-robotic-navigation-a","title":"Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models","date":"2025-01-07","arxiv_id":"2501.05478","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-semantically-aware-kernel-enhanced-and","title":"DPO Kernels: A Semantically-Aware, Kernel-Enhanced, and Divergence-Rich Paradigm for Direct Preference Optimization","date":"2025-01-05","arxiv_id":"2501.03271","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-following-pruning-for-large","title":"Instruction-Following Pruning for Large Language Models","date":"2025-01-03","arxiv_id":"2501.02086","repositories_listed":0,"syntology":null},{"url":null,"slug":"hsi-gpt-a-general-purpose-large-scene-motion","title":"HSI-GPT: A General-Purpose Large Scene-Motion-Language Model for Human Scene Interaction","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mimo-a-medical-vision-language-model-with","title":"MIMO: A Medical Vision Language Model with Visual Referring Multimodal Input and Pixel Grounding Multimodal Output","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"slade-shielding-against-dual-exploits-in","title":"SLADE: Shielding against Dual Exploits in Large Vision-Language Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hindsight-planner-a-closed-loop-few-shot","title":"Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following","date":"2024-12-27","arxiv_id":"2412.19562","repositories_listed":0,"syntology":null},{"url":null,"slug":"internalized-self-correction-for-large","title":"Internalized Self-Correction for Large Language Models","date":"2024-12-21","arxiv_id":"2412.16653","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnlm-improving-gemini-for-learning","title":"LearnLM: Improving Gemini for Learning","date":"2024-12-21","arxiv_id":"2412.16429","repositories_listed":0,"syntology":null},{"url":null,"slug":"length-controlled-generation-for-black-box","title":"Length Controlled Generation for Black-box LLMs","date":"2024-12-19","arxiv_id":"2412.14656","repositories_listed":0,"syntology":null},{"url":null,"slug":"systematic-evaluation-of-long-context-llms-on","title":"Systematic Evaluation of Long-Context LLMs on Financial Concepts","date":"2024-12-19","arxiv_id":"2412.15386","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-examination-of-preference","title":"A Systematic Examination of Preference Learning through the Lens of Instruction-Following","date":"2024-12-18","arxiv_id":"2412.15282","repositories_listed":0,"syntology":null},{"url":null,"slug":"metamorph-multimodal-understanding-and","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","date":"2024-12-18","arxiv_id":"2412.14164","repositories_listed":0,"syntology":null},{"url":null,"slug":"pipeline-analysis-for-developing-instruct","title":"Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque","date":"2024-12-18","arxiv_id":"2412.13922","repositories_listed":0,"syntology":null},{"url":null,"slug":"question-how-do-large-language-models-perform","title":"Question: How do Large Language Models perform on the Question Answering tasks? Answer:","date":"2024-12-17","arxiv_id":"2412.12893","repositories_listed":0,"syntology":null},{"url":null,"slug":"chipalign-instruction-alignment-in-large","title":"ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolation","date":"2024-12-15","arxiv_id":"2412.19819","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-llms-to-understand-and-generate","title":"Empowering LLMs to Understand and Generate Complex Vector Graphics","date":"2024-12-15","arxiv_id":"2412.11102","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-vision-language-model-as","title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval","date":"2024-12-15","arxiv_id":"2412.11087","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlr-bench-multilingual-benchmark-dataset-for","title":"VLR-Bench: Multilingual Benchmark Dataset for Vision-Language Retrieval Augmented Generation","date":"2024-12-13","arxiv_id":"2412.10151","repositories_listed":0,"syntology":null},{"url":null,"slug":"easyref-omni-generalized-group-image","title":"EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM","date":"2024-12-12","arxiv_id":"2412.09618","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-zip-adaptive-visual-token-compression","title":"LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information","date":"2024-12-11","arxiv_id":"2412.08771","repositories_listed":0,"syntology":null},{"url":null,"slug":"smoltulu-higher-learning-rate-to-batch-size","title":"SmolTulu: Higher Learning Rate to Batch Size Ratios Can Lead to Better Reasoning in SLMs","date":"2024-12-11","arxiv_id":"2412.08347","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-for-generalizable-language-conditioned","title":"LLMs for Generalizable Language-Conditioned Policy Learning under Minimal Data Requirements","date":"2024-12-09","arxiv_id":"2412.06877","repositories_listed":0,"syntology":null},{"url":null,"slug":"groot-2-weakly-supervised-multi-modal","title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents","date":"2024-12-07","arxiv_id":"2412.10410","repositories_listed":0,"syntology":null},{"url":null,"slug":"exaone-3-5-series-of-large-language-models","title":"EXAONE 3.5: Series of Large Language Models for Real-world Use Cases","date":"2024-12-06","arxiv_id":"2412.04862","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-align-utilizing-large-language-models-for","title":"LLM-Align: Utilizing Large Language Models for Entity Alignment in Knowledge Graphs","date":"2024-12-06","arxiv_id":"2412.04690","repositories_listed":0,"syntology":null},{"url":null,"slug":"if-you-can-t-use-them-recycle-them-optimizing","title":"If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs","date":"2024-12-05","arxiv_id":"2412.04144","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-words-to-workflows-automating-business","title":"From Words to Workflows: Automating Business Processes","date":"2024-12-04","arxiv_id":"2412.03446","repositories_listed":0,"syntology":null},{"url":null,"slug":"vidhalluc-evaluating-temporal-hallucinations","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","date":"2024-12-04","arxiv_id":"2412.03735","repositories_listed":0,"syntology":null}],"record_sha256":"6f9208fb5c6d74811d3df1b724a841ffd2a486639aaf66af296845b700a05a68","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}