Skip to content
View Kaleemullahqasim's full-sized avatar

Block or report Kaleemullahqasim

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Kaleemullahqasim/README.md

Kaleem Ullah Qasim

PhD Candidate in Artificial Intelligence · Southwest Jiaotong University, Chengdu Lead Researcher, Huawei commissioned research contract (2025 to Jan 2027)

I make language models reason more reliably and run more cheaply. Three lines: verified decomposition instead of one long chain of thought, inference that fits on-device by treating the KV cache as redundant, and agent teams that coordinate through local rules with no orchestrator. The newer work takes its mechanism from biology, tests it honestly, and reports where the analogy breaks.

27 papers · 11 published or accepted · first author on 20 · Google Scholar · ORCID · CV

Graduating 2026 and open to research and applied LLM roles. Reach me at kaleem@my.swjtu.edu.cn.


Currently

  • Verified-residency quantization on the Apple Neural Engine. Most published on-device numbers are invalid because the model silently falls back to CPU or GPU. Building the protocol that catches it.
  • Cache-less transformers. Training decoders that never materialise a KV cache, by stabilising the residual stream instead.
  • Bio-grounded agent coordination. Frozen identical agents covering distinct roles through lateral inhibition, no scheduler involved.

Research Threads

Structured and verifiable reasoning. RDoLT replaced the single long chain of thought with a verified sub-problem tree that carries knowledge between branches. The programme since then pushes on process-level verifiable rewards trained with GRPO, curriculum-scheduled recursion depth, and a destroy-repair search over reasoning chains that improves small models with no extra training.

Efficient inference and the KV cache. A sustained argument that the cache is largely redundant: keys and values can be recovered exactly from the residual stream for lossless decoding at bounded memory, stabilising that stream lets a decoder train cache-free from the outset, and characterising reachable cache states bounds what any residual compression scheme can achieve.

On-device reasoning on consumer NPUs. Published on-device numbers are often invalid because the model silently falls back to CPU or GPU. I built a four-signal residency protocol that gates every measurement, applied it to LUT4/6/8 and FP16 builds of Llama-3.2-1B on the Apple Neural Engine, and exposed a precision-independent weight-traffic floor in the decode path.

Decentralised multi-agent coordination. Identical frozen agents organising through local rules rather than a scheduler: asynchronous lateral inhibition for role coverage, task-dependent latent collaboration for deciding when agents should share state at all, residual replay for compact lossless agent-to-agent communication. These measure coordination cost, not accuracy alone.


Selected Publications

Destroy-Repair of Reasoning Chains via Adaptive Large Neighborhood Search in Small Language Models Kaleem Ullah Qasim, Jiashu Zhang, Muhammad Waqas Aslam, Muhammad Kashif Shaheen Information Sciences 758:123959, 2027 (online Aug 2026) · JCR Q1, CAS Tier 1, IF 8.1, CCF-B doi:10.1016/j.ins.2026.123959

MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction Kaleem Ullah Qasim, Jiashu Zhang IEEE Transactions on Intelligent Transportation Systems, accepted 2026, in press · JCR Q1, CAS Tier 1, CCF-B

Recursive Decomposition of Logical Thoughts (RDoLT) Kaleem Ullah Qasim, Jiashu Zhang, Tariq Alsahfi, Ateeq Ur Rehman Butt Journal of Artificial Intelligence Research 83, Article 27, 2025 · SJR Q1, CCF-B · 20 citations doi:10.1613/jair.1.18562

More publications

Understanding the Business of Online Affiliate Marketing: An Empirical Study Haitao Xu, Yiwen Sun, Kaleem Ullah Qasim, et al. IEEE INFOCOM 2025, 1-10 · CCF-A doi:10.1109/INFOCOM55648.2025.11044696

TraffiCoT-R: Advanced Spatio-Temporal Reasoning in Large Language Models Tariq Alsahfi, Kaleem Ullah Qasim Alexandria Engineering Journal 128:464-475, 2025 · JCR Q1 · 5 citations doi:10.1016/j.aej.2025.05.027

Complexity Aware Recursive Decomposition for Math Reasoning Kaleem Ullah Qasim, Jiashu Zhang, Hafiz Sami Ur Rehman ACM EILM '25, 118-121 doi:10.1145/3788731.3788750

From Data to Decisions: Enhancing Financial Forecasts with LSTM for AI Token Prices Rizwan Ali, Jian Xu, et al., Kaleem Ullah Qasim (corresponding) Journal of Economic Studies 51(8):1677-1693, 2024 · 12 citations doi:10.1108/JES-01-2024-0022

Also co-authored in Archives of Computational Methods in Engineering (2026), Journal of Manufacturing Systems (2026), Computers & Operations Research (2026), and Springer CCIS (2026).

16 further first-author manuscripts are under review or revision at Information Fusion, IEEE TMC, IEEE/ACM TASLP, Information Processing & Management, Neural Networks, Neurocomputing, Applied Soft Computing, and Journal of Systems Architecture.

Full list on Google Scholar


Research Code

Each manuscript ships a public repository carrying the method and reported numbers while under review; the full implementation is released on acceptance.

Repository What it is
CGAR Curriculum-guided adaptive recursion. Cuts tiny-recursive-model training from 10.93 to 6.38 hours on 423k Sudoku-Extreme puzzles, 1.71× for 0.63 points of accuracy. Full training, ablation and verification suite
KV-Direct Lossless bounded-memory inference via exact KV recovery from the residual stream
KV-Free-Transformers Training cache-less decoders through residual stream stabilisation
sliding-window-wall Reachable KV state and the limits of residual compression in hybrid-attention models
lateral-inhibition-llm-agents Decentralised asynchronous lateral inhibition for role coverage in homogeneous agent teams
latent-collab-mas Task-dependent latent collaboration in multi-agent systems
NL-CGAR Routing natural-language problems to curriculum-guided recursive experts
RDC Recursive decomposition cache: hierarchical query decomposition for semantic caching

Tools

openbanana converts static diagram images and PDFs back into editable DrawIO XML, using fine-tuned SAM3 segmentation and locally run vision-language models. Built for reconstructing figures whose sources were lost.


Engineering

The research runs on systems I ship. Hybrid RAG over enterprise document corpora (Qdrant, FastAPI, containerised, with retrieval-quality regression tests so answer quality cannot silently rot). Multi-agent orchestration with tool calling, routing and retry policies. Fine-tuning and quantisation for on-premise deployments where data cannot leave the building. Top Rated on Upwork across 20+ client projects.

Stack. PyTorch · HuggingFace (Transformers, TRL, PEFT) · vLLM · LoRA/QLoRA · GRPO and DPO · MLX and CoreML on Apple silicon · Huawei Ascend · LangGraph and MCP · Qdrant · Docker · Python


Links

Google Scholar · ORCID · CV · LinkedIn · Hugging Face · Upwork

Contact: kaleem@my.swjtu.edu.cn

Pinned Loading

  1. KV-Direct KV-Direct Public

    KV-Direct: lossless bounded-memory LLM inference via exact KV recovery from the residual stream. Paper under review at Journal of Systems Architecture

    9 3

  2. CGAR CGAR Public

    CGAR: curriculum-guided adaptive recursion. 1.71x faster training for tiny recursive reasoning models (10.93h to 6.38h on 423k Sudoku-Extreme puzzles)

    Python 7 1

  3. openbanana openbanana Public

    🍌 OpenBanana — Convert static diagram images and PDFs into fully editable DrawIO XML using fine-tuned SAM3 segmentation and local VLMs

    Python 1

  4. KV-Free-Transformers KV-Free-Transformers Public

    Training cache-less transformer decoders via residual stream stabilisation. Paper under review at Engineering Applications of Artificial Intelligence

  5. NL-CGAR NL-CGAR Public

    NL-CGAR: routing natural-language problems to curriculum-guided recursive reasoning experts. Paper under review at Expert Systems with Applications

    Python

  6. sliding-window-wall sliding-window-wall Public

    Reachable KV cache states and the limits of residual compression in hybrid-attention language models. Paper under review at The Journal of Supercomputing